{"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":"2026-09-26T08:55:16Z","heatmap_track_id":"full_freedom/intensive","models":[{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-astra:ae2dbe5eab26d175","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":1.30343,"median":1.3074612499999998,"min":1.077205,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":10.42744},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.27234},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.26443,"mean":0.23918625000000002,"median":0.241805,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":1.91349}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.48718,"mean":0.4090425,"median":0.40659249999999997,"min":0.311405,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":3.2723400000000002},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.26443,"mean":0.23918625000000002,"median":0.241805,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":1.91349},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":1.30343,"median":1.3074612499999998,"min":1.077205,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":8},"run_count":8,"token_priced_attempt_count":8,"total":10.42744}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":24},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":1.47583,"mean":0.6505529166666667,"median":0.40659249999999997,"min":0.2072175,"pricing_table_versions":{"boardgame-list-prices-2026-09-05":24},"run_count":24,"token_priced_attempt_count":24,"total":15.613269999999998},"codegen_output_tokens":{"attempt_count":24,"output_max":27674,"output_mean":11074.333333333334,"output_min":2260,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":27674,"output_mean":24131.875,"output_min":19038,"run_count":8},"medium":{"attempt_count":8,"output_max":7733,"output_mean":6244.125,"output_min":3722,"run_count":8},"none":{"attempt_count":8,"output_max":3278,"output_mean":2847.0,"output_min":2260,"run_count":8}},"display_name":"GPT-6 Astra","economics":{"all":84.04123566318927,"highest":94.7546227189803,"medium":80.80438777539894,"none":76.56469649518856},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":24,"finish_reasons":["stop"],"indexed_attempts":24,"output_token_observations":24,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":24,"reconciliation_get_attempt_observations":24,"total_output_tokens":265784,"total_reasoning_output_tokens":150836,"total_visible_output_tokens":114948,"visible_token_observations":24},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"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-6-astra","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"gpt-6-astra","is_recent_addition":false,"last_measured_at":"2026-09-26T05:25:00Z","match_totals_all":{"draws":557,"losses":463,"wins":4918},"match_totals_tracks":{"highest":{"draws":63,"losses":82,"wins":1807},"medium":{"draws":206,"losses":165,"wins":1623},"none":{"draws":288,"losses":216,"wins":1488}},"model_slug":"gpt-6-astra","overall":{"max":100.0,"mean":84.04123566318925,"min":50.786487957815275},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":94.41850246625869,"GB2-02":100.0,"GB2-03":100.0,"GB2-04":99.09804118591246,"GB2-05":99.99999999999999,"GB2-06":84.91016196304786,"GB2-07":99.99999999999999,"GB2-08":79.61027613662344},"per_game_all":{"GB2-01":79.13720356062241,"GB2-02":70.73241096235002,"GB2-03":80.40630598536252,"GB2-04":92.26768919050777,"GB2-05":94.42363514263202,"GB2-06":81.56292987420873,"GB2-07":97.28911626460264,"GB2-08":76.51059432522801},"per_game_match_totals_all":{"GB2-01":{"draws":33,"losses":87,"wins":608},"GB2-02":{"draws":213,"losses":31,"wins":488},"GB2-03":{"draws":180,"losses":32,"wins":508},"GB2-04":{"draws":67,"losses":52,"wins":599},"GB2-05":{"draws":0,"losses":23,"wins":685},"GB2-06":{"draws":64,"losses":91,"wins":581},"GB2-07":{"draws":0,"losses":22,"wins":778},"GB2-08":{"draws":0,"losses":125,"wins":671}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":7,"wins":217},"GB2-02":{"draws":12,"losses":3,"wins":223},"GB2-03":{"draws":8,"losses":1,"wins":229},"GB2-04":{"draws":18,"losses":8,"wins":212},"GB2-05":{"draws":0,"losses":0,"wins":244},"GB2-06":{"draws":25,"losses":23,"wins":196},"GB2-07":{"draws":0,"losses":4,"wins":254},"GB2-08":{"draws":0,"losses":36,"wins":232}},"medium":{"GB2-01":{"draws":21,"losses":65,"wins":162},"GB2-02":{"draws":79,"losses":9,"wins":148},"GB2-03":{"draws":67,"losses":8,"wins":163},"GB2-04":{"draws":22,"losses":12,"wins":202},"GB2-05":{"draws":0,"losses":16,"wins":216},"GB2-06":{"draws":17,"losses":25,"wins":212},"GB2-07":{"draws":0,"losses":9,"wins":275},"GB2-08":{"draws":0,"losses":21,"wins":245}},"none":{"GB2-01":{"draws":12,"losses":15,"wins":229},"GB2-02":{"draws":122,"losses":19,"wins":117},"GB2-03":{"draws":105,"losses":23,"wins":116},"GB2-04":{"draws":27,"losses":32,"wins":185},"GB2-05":{"draws":0,"losses":7,"wins":225},"GB2-06":{"draws":22,"losses":43,"wins":173},"GB2-07":{"draws":0,"losses":9,"wins":249},"GB2-08":{"draws":0,"losses":68,"wins":194}}},"per_game_raw_elo_all":{"GB2-01":1993.6121847289148,"GB2-02":1857.6836680824936,"GB2-03":1955.5465221966922,"GB2-04":1932.8725877217084,"GB2-05":2219.1219102346963,"GB2-06":2014.1822269415225,"GB2-07":2255.5215319505846,"GB2-08":2014.1846256606996},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2205.8688455146457,"GB2-02":2066.890409487723,"GB2-03":2164.6319931823346,"GB2-04":1977.4723757158326,"GB2-05":2307.351272343375,"GB2-06":2069.683701788402,"GB2-07":2296.8473057603164,"GB2-08":2054.0188035797332},"medium":{"GB2-01":1673.0334228608901,"GB2-02":1791.560695627348,"GB2-03":1970.9625493936694,"GB2-04":1946.0633546395002,"GB2-05":2081.07816353817,"GB2-06":2071.3650838432304,"GB2-07":2213.9870048414227,"GB2-08":2156.9721829025484},"none":{"GB2-01":2101.9342858112086,"GB2-02":1714.5998991324095,"GB2-03":1731.0450240140724,"GB2-04":1875.0820328097927,"GB2-05":2268.9362948225444,"GB2-06":1901.4978951929347,"GB2-07":2255.730285250015,"GB2-08":1831.5628904998168}},"per_game_tracks":{"highest":{"GB2-01":94.41850246625869,"GB2-02":100.0,"GB2-03":100.0,"GB2-04":99.09804118591246,"GB2-05":99.99999999999999,"GB2-06":84.91016196304786,"GB2-07":99.99999999999999,"GB2-08":79.61027613662344},"medium":{"GB2-01":55.9690411109274,"GB2-02":61.41074492923479,"GB2-03":81.84173515159739,"GB2-04":94.26355743174413,"GB2-05":85.72785548150513,"GB2-06":85.04223459370405,"GB2-07":94.59003202317284,"GB2-08":87.58990148130579},"none":{"GB2-01":87.02406710468114,"GB2-02":50.786487957815275,"GB2-03":59.3771828044902,"GB2-04":83.44146895386669,"GB2-05":97.54304994639097,"GB2-06":74.7363930658743,"GB2-07":97.27731677063512,"GB2-08":62.33160535775479}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":94.7546227189803,"medium":80.80438777539894,"none":76.56469649518856},"reasoning_agg":{"highest":{"max":100.0,"mean":94.7546227189803,"min":79.61027613662344},"medium":{"max":94.59003202317284,"mean":80.80438777539894,"min":55.9690411109274},"none":{"max":97.54304994639097,"mean":76.56469649518856,"min":50.786487957815275}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":90.63728300006002,"reasoning_variance":18.189926223791744,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.596047336870768},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":94.55632421087999,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.1982985081003079},"medium":{"ceiling_score":94.59003202317284,"expected_score":88.98551748566817,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":8.181129710269232},"none":{"ceiling_score":97.54304994639097,"expected_score":88.37000730363188,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":11.805310808443323}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5-1:4036efb3e80cec89","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":5.021086745700856,"median":3.933625,"min":2.3764558334148846,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3,"boardgame-list-prices-2026-09-08":10},"run_count":11,"token_priced_attempt_count":13,"total":48.73911793121369},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276065},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.33905201032609}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":1.511677676840267,"mean":1.1541937045345083,"median":1.126127596791556,"min":0.7961115304367101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":9.233549636276065},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.8940315948861309,"mean":0.7923815012907612,"median":0.7948316688813246,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":6.33905201032609},"historical-provider-setting-intensive":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":5.021086745700856,"median":3.933625,"min":2.3764558334148846,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":3,"boardgame-list-prices-2026-09-08":10},"run_count":11,"token_priced_attempt_count":13,"total":48.739117931213684}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":11.79121,"mean":2.3225539838420417,"median":1.126127596791556,"min":0.6566066208996896,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":20,"boardgame-list-prices-2026-09-08":10},"run_count":27,"token_priced_attempt_count":30,"total":64.31171957781585},"codegen_output_tokens":{"attempt_count":35,"output_max":231035,"output_mean":46647.59375,"output_min":5610,"run_count":32},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":18,"output_max":231035,"output_mean":80471.125,"output_min":38285,"run_count":16},"medium":{"attempt_count":9,"output_max":25949,"output_mean":17238.625,"output_min":9715,"run_count":8},"none":{"attempt_count":8,"output_max":10198,"output_mean":8409.5,"output_min":5610,"run_count":8}},"display_name":"Claude Fable 5.1","economics":{"all":80.6583012148468,"highest":92.14999700185413,"medium":76.04007393799117,"none":73.78483270469505},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":10,"effective_max_output_tokens":[128000],"finish_reason_observations":30,"finish_reasons":["end_turn","stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"requested_max_output_token_observations":10,"requested_max_output_tokens":[128000],"total_output_tokens":1492723,"total_reasoning_output_tokens":1266567,"total_visible_output_tokens":226156,"visible_token_observations":35},"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-5-1","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":11,"evaluated_cells":11,"first_pass_admitted":9,"first_pass_rate":0.8181818181818182,"infra_excluded_game_aliases":["GB2-01","GB2-02","GB2-05","GB2-06","GB2-08"],"infra_failures_excluded":5,"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":0.18181818181818182}},"id":"claude-fable-5-1","is_recent_addition":false,"last_measured_at":"2026-09-26T07:12:13Z","match_totals_all":{"draws":457,"losses":613,"wins":5518},"match_totals_tracks":{"highest":{"draws":72,"losses":148,"wins":2432},"medium":{"draws":163,"losses":241,"wins":1576},"none":{"draws":222,"losses":224,"wins":1510}},"model_slug":"claude-fable-5-1","overall":{"max":100.0,"mean":80.65830121484679,"min":33.611544188954454},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":82.6699612820177,"GB2-02":94.06267507939037,"GB2-03":89.87794380317823,"GB2-04":84.43395767460939,"GB2-05":91.96094632299464,"GB2-06":100.0,"GB2-07":94.19449185264283,"GB2-08":99.99999999999999},"per_game_all":{"GB2-01":74.23821078043866,"GB2-02":80.232820070839,"GB2-03":85.15424925974268,"GB2-04":57.65464970994384,"GB2-05":89.29601167237188,"GB2-06":86.04305858129254,"GB2-07":88.34413932569187,"GB2-08":84.30327031845384},"per_game_match_totals_all":{"GB2-01":{"draws":1,"losses":24,"wins":209},"GB2-02":{"draws":10,"losses":8,"wins":212},"GB2-03":{"draws":4,"losses":8,"wins":218},"GB2-04":{"draws":18,"losses":17,"wins":209},"GB2-05":{"draws":0,"losses":13,"wins":211},"GB2-06":{"draws":7,"losses":2,"wins":233},"GB2-07":{"draws":0,"losses":17,"wins":241},"GB2-08":{"draws":0,"losses":4,"wins":258}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":24,"wins":209},"GB2-02":{"draws":10,"losses":8,"wins":212},"GB2-03":{"draws":4,"losses":8,"wins":218},"GB2-04":{"draws":18,"losses":17,"wins":209},"GB2-05":{"draws":0,"losses":13,"wins":211},"GB2-06":{"draws":7,"losses":2,"wins":233},"GB2-07":{"draws":0,"losses":17,"wins":241},"GB2-08":{"draws":0,"losses":4,"wins":258}}},"per_game_raw_elo_all":{"GB2-01":1925.8410842542553,"GB2-02":1926.1325134402143,"GB2-03":2006.5873471775021,"GB2-04":1707.3432758540002,"GB2-05":2137.645701923589,"GB2-06":2088.517440394999,"GB2-07":2120.8101092469497,"GB2-08":2114.3728653796525},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2042.8857991648467,"GB2-02":2024.955763958844,"GB2-03":2057.118044627654,"GB2-04":1881.7118633240975,"GB2-05":2180.6442776095546,"GB2-06":2319.7163862821803,"GB2-07":2209.1268234021427,"GB2-08":2317.1313290002845},"medium":{"GB2-01":1793.818548037135,"GB2-02":1970.261060326033,"GB2-03":1975.0192770069198,"GB2-04":1550.539291425385,"GB2-05":2102.6133670057834,"GB2-06":2017.1078884450108,"GB2-07":2173.2512797521044,"GB2-08":2067.7734288744737},"none":{"GB2-01":1940.818905560784,"GB2-02":1783.1807160357664,"GB2-03":1987.6247198979324,"GB2-04":1689.7786728125182,"GB2-05":2129.6794611554287,"GB2-06":1928.728046457806,"GB2-07":1980.0522245866011,"GB2-08":1958.2138382642}},"per_game_tracks":{"highest":{"GB2-01":82.6699612820177,"GB2-02":94.06267507939037,"GB2-03":89.87794380317823,"GB2-04":84.43395767460939,"GB2-05":91.96094632299464,"GB2-06":100.0,"GB2-07":94.19449185264283,"GB2-08":99.99999999999999},"medium":{"GB2-01":64.74226485417809,"GB2-02":86.38382141564267,"GB2-03":82.21187572251407,"GB2-04":33.611544188954454,"GB2-05":87.08229574486306,"GB2-06":81.7358023522556,"GB2-07":91.82829306510236,"GB2-08":80.72469416041906},"none":{"GB2-01":75.3024062051202,"GB2-02":60.25196371748394,"GB2-03":83.37292825353573,"GB2-04":54.91844726626767,"GB2-05":88.84479294925792,"GB2-06":76.393373391622,"GB2-07":79.00963305933045,"GB2-08":72.18511679494245}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":92.14999700185413,"medium":76.04007393799117,"none":73.78483270469505},"reasoning_agg":{"highest":{"max":100.0,"mean":92.14999700185413,"min":82.6699612820177},"medium":{"max":91.82829306510236,"mean":76.04007393799117,"min":33.611544188954454},"none":{"max":88.84479294925792,"mean":73.78483270469505,"min":54.91844726626767}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":87.43354058292516,"reasoning_variance":18.365164297159083,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.775239368078374},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":91.9165748964588,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.23342210539533426},"medium":{"ceiling_score":91.82829306510236,"expected_score":84.40236971995219,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":8.362295781961024},"none":{"ceiling_score":88.84479294925792,"expected_score":85.9816771323645,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":12.196844427669447}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5-5:90223050ff456e01","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":1.98688675,"median":1.871197,"min":1.357152,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":9,"token_priced_attempt_count":11,"total":17.677191999999998},"medium":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.728964,"mean":0.33381875,"median":0.267474,"min":0.167816,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":9,"token_priced_attempt_count":10,"total":3.0063080000000006},"none":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124844,"mean":0.11677924999999999,"median":0.118817,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":9,"token_priced_attempt_count":9,"total":1.052792}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.728964,"mean":0.33381875,"median":0.267474,"min":0.167816,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"run_count":9,"token_priced_attempt_count":10,"total":3.0063079999999998},"historical-provider-setting-baseline":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.124844,"mean":0.11677924999999999,"median":0.118817,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":9,"token_priced_attempt_count":9,"total":1.052792},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":1.98688675,"median":1.871197,"min":1.357152,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"run_count":9,"token_priced_attempt_count":11,"total":17.677192}},"codegen_cost_usd":{"admitted_cell_count":26,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":30},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":3.092384,"mean":0.8124949166666666,"median":0.267474,"min":0.094852,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":30},"run_count":27,"token_priced_attempt_count":30,"total":21.736292},"codegen_output_tokens":{"attempt_count":30,"output_max":149830,"output_mean":37334.40740740741,"output_min":2400,"run_count":27},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":149830,"output_mean":94967.22222222222,"output_min":65515,"run_count":9},"medium":{"attempt_count":10,"output_max":31033,"output_mean":13777.666666666666,"output_min":6104,"run_count":9},"none":{"attempt_count":9,"output_max":3890,"output_mean":3258.3333333333335,"output_min":2400,"run_count":9}},"display_name":"Claude Opus 5.5","economics":{"all":72.28869304000276,"highest":81.92398481180655,"medium":75.53619388185062,"none":59.40590042635111},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":30,"effective_max_output_tokens":[65536,128000],"finish_reason_observations":30,"finish_reasons":["end_turn","max_tokens"],"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,"requested_max_output_token_observations":30,"requested_max_output_tokens":[65536,128000],"total_output_tokens":1008029,"total_reasoning_output_tokens":820640,"total_visible_output_tokens":187389,"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":"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":"anthropic","provider_model":"claude-opus-5-5","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":9,"evaluated_cells":9,"first_pass_admitted":8,"first_pass_rate":0.8888888888888888,"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":0.1111111111111111},"baseline":{"admitted_plugins":9,"evaluated_cells":9,"first_pass_admitted":9,"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":6,"first_pass_rate":0.75,"infra_excluded_game_aliases":["GB2-08"],"infra_failures_excluded":1,"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":"claude-opus-5-5","is_recent_addition":false,"last_measured_at":"2026-09-26T05:45:11Z","match_totals_all":{"draws":191,"losses":261,"wins":2038},"match_totals_tracks":{"highest":{"draws":22,"losses":39,"wins":701},"medium":{"draws":28,"losses":62,"wins":768},"none":{"draws":141,"losses":160,"wins":569}},"model_slug":"claude-opus-5-5","overall":{"max":92.59219547409448,"mean":72.28869304000276,"min":33.278664420345756},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.24992015349287,"GB2-02":83.87796377875198,"GB2-03":79.65389601007746,"GB2-04":92.59219547409448,"GB2-05":86.45902117348551,"GB2-06":86.93088640295221,"GB2-07":88.06824608412906,"GB2-08":78.55974941746881},"per_game_all":{"GB2-01":68.60188509334586,"GB2-02":71.19623804898866,"GB2-03":61.53373484531793,"GB2-04":69.73146018580648,"GB2-05":79.05695219526918,"GB2-06":78.182770379991,"GB2-07":83.52298405891055,"GB2-08":66.48351951239248},"per_game_match_totals_all":{"GB2-01":{"draws":12,"losses":28,"wins":218},"GB2-02":{"draws":31,"losses":14,"wins":251},"GB2-03":{"draws":54,"losses":22,"wins":128},"GB2-04":{"draws":74,"losses":23,"wins":191},"GB2-05":{"draws":0,"losses":25,"wins":239},"GB2-06":{"draws":16,"losses":23,"wins":249},"GB2-07":{"draws":0,"losses":19,"wins":299},"GB2-08":{"draws":4,"losses":107,"wins":463}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":21,"wins":60},"GB2-02":{"draws":5,"losses":1,"wins":96},"GB2-03":{"draws":1,"losses":0,"wins":67},"GB2-04":{"draws":12,"losses":3,"wins":83},"GB2-05":{"draws":0,"losses":2,"wins":82},"GB2-06":{"draws":1,"losses":0,"wins":97},"GB2-07":{"draws":0,"losses":1,"wins":107},"GB2-08":{"draws":0,"losses":11,"wins":109}},"medium":{"GB2-01":{"draws":4,"losses":2,"wins":80},"GB2-02":{"draws":3,"losses":4,"wins":87},"GB2-03":{"draws":3,"losses":7,"wins":56},"GB2-04":{"draws":10,"losses":11,"wins":75},"GB2-05":{"draws":0,"losses":14,"wins":78},"GB2-06":{"draws":8,"losses":7,"wins":85},"GB2-07":{"draws":0,"losses":9,"wins":95},"GB2-08":{"draws":0,"losses":8,"wins":212}},"none":{"GB2-01":{"draws":5,"losses":5,"wins":78},"GB2-02":{"draws":23,"losses":9,"wins":68},"GB2-03":{"draws":50,"losses":15,"wins":5},"GB2-04":{"draws":52,"losses":9,"wins":33},"GB2-05":{"draws":0,"losses":9,"wins":79},"GB2-06":{"draws":7,"losses":16,"wins":67},"GB2-07":{"draws":0,"losses":9,"wins":97},"GB2-08":{"draws":4,"losses":88,"wins":142}}},"per_game_raw_elo_all":{"GB2-01":1865.2085512812603,"GB2-02":1875.5084485812924,"GB2-03":1776.6554223270284,"GB2-04":1800.764016436605,"GB2-05":1991.2292421165814,"GB2-06":1973.34999187783,"GB2-07":2061.8351567931454,"GB2-08":1897.4872849285032},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1736.4247654132985,"GB2-02":1965.3554188763624,"GB2-03":1969.9083455607108,"GB2-04":1949.3857873933603,"GB2-05":2109.884704160461,"GB2-06":2117.798707349202,"GB2-07":2130.116345399201,"GB2-08":2052.452083354375},"medium":{"GB2-01":1947.9736061841902,"GB2-02":1927.5705341330538,"GB2-03":1885.4539916562844,"GB2-04":1792.4396032241075,"GB2-05":1876.9521190154462,"GB2-06":1986.7256877898253,"GB2-07":2049.1898711983813,"GB2-08":2041.53277651581},"none":{"GB2-01":1911.2272822462924,"GB2-02":1733.5993927344612,"GB2-03":1474.60392976409,"GB2-04":1660.4666586923474,"GB2-05":1986.8509031738374,"GB2-06":1815.5255804944622,"GB2-07":2006.199253781853,"GB2-08":1598.4769949153242}},"per_game_tracks":{"highest":{"GB2-01":59.24992015349287,"GB2-02":83.87796377875198,"GB2-03":79.65389601007746,"GB2-04":92.59219547409448,"GB2-05":86.45902117348551,"GB2-06":86.93088640295221,"GB2-07":88.06824608412906,"GB2-08":78.55974941746881},"medium":{"GB2-01":74.58943650619462,"GB2-02":78.35646119894932,"GB2-03":71.66864410553056,"GB2-04":68.4552557371941,"GB2-05":71.92890687874986,"GB2-06":79.04126853940939,"GB2-07":82.66159163036188,"GB2-08":77.58798645841534},"none":{"GB2-01":71.96629862035006,"GB2-02":51.35428916926469,"GB2-03":33.278664420345756,"GB2-04":48.14692934613087,"GB2-05":78.78292853357216,"GB2-06":68.57615619761141,"GB2-07":79.83911446224074,"GB2-08":43.302822661293256}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":81.92398481180655,"medium":75.53619388185062,"none":59.40590042635111},"reasoning_agg":{"highest":{"max":92.59219547409448,"mean":81.92398481180655,"min":59.24992015349287},"medium":{"max":82.66159163036188,"mean":75.53619388185062,"min":68.4552557371941},"none":{"max":79.83911446224074,"mean":59.40590042635111,"min":33.278664420345756}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":92.59219547409448,"expected_score":78.6603100562291,"reasoning_variance":22.518084385455438,"reliability_score":92.09919557917608,"uncertainty_avg":7.900804420823919,"uncertainty_penalty":6.371617016226338},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":92.59219547409448,"expected_score":81.36713659880954,"reliability_score":92.27821742475605,"uncertainty_avg":7.721782575243947,"uncertainty_penalty":-0.5568482129970107},"medium":{"ceiling_score":82.66159163036188,"expected_score":84.55200981635889,"reliability_score":91.9231623105566,"uncertainty_avg":8.076837689443389,"uncertainty_penalty":9.015815934508268},"none":{"ceiling_score":79.83911446224074,"expected_score":70.06178375351888,"reliability_score":92.09620700221558,"uncertainty_avg":7.903792997784414,"uncertainty_penalty":10.655883327167771}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-5:2db917d562130aa3","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"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},"cost_is_complete":false,"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":7.138874999999999},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.5221625,"mean":0.2856328125,"median":0.2536225,"min":0.2178175,"pricing_table_versions":{"boardgame-list-prices-2026-07-25":16},"run_count":16,"token_priced_attempt_count":16,"total":4.570124999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"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},"historical-provider-setting-baseline":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"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},"historical-provider-setting-intensive":{"admitted_cell_count":13,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":16},"cost_is_complete":false,"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},"cost_is_complete":false,"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":33.78345000000001},"codegen_latency_ms":{"attempt_count":48,"max_ms":999214,"mean_ms":286075.0416666667,"min_ms":51907,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":16,"max_ms":999214,"mean_ms":596693.625,"min_ms":340056,"run_count":16},"medium":{"attempt_count":16,"max_ms":302283,"mean_ms":172049.4375,"min_ms":111251,"run_count":16},"none":{"attempt_count":16,"max_ms":344404,"mean_ms":89482.0625,"min_ms":51907,"run_count":16}},"codegen_output_tokens":{"attempt_count":48,"output_max":88360,"output_mean":25640.5,"output_min":5404,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":16,"output_max":88360,"output_mean":52673.75,"output_min":31102,"run_count":16},"medium":{"attempt_count":16,"output_max":25625,"output_mean":15334.8125,"output_min":9676,"run_count":16},"none":{"attempt_count":16,"output_max":28699,"output_mean":8912.9375,"output_min":5404,"run_count":16}},"display_name":"Claude Opus 5","economics":{"all":64.86462198025177,"highest":77.66650262610439,"medium":61.96473232169259,"none":59.15550053550422},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T06:36:29Z","match_totals_all":{"draws":1193,"losses":1382,"wins":6018},"match_totals_tracks":{"highest":{"draws":157,"losses":329,"wins":1938},"medium":{"draws":395,"losses":498,"wins":2091},"none":{"draws":641,"losses":555,"wins":1989}},"model_slug":"claude-opus-5","overall":{"max":90.57193620024879,"mean":63.6271131855029,"min":15.44348716732651},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":60.75327500594525,"GB2-02":66.71678962770099,"GB2-03":90.4111038614959,"GB2-04":75.66030745243378,"GB2-05":90.57193620024879,"GB2-07":88.98341049342496,"GB2-08":70.56869574148102},"per_game_all":{"GB2-01":60.34768164182535,"GB2-02":52.42983772443525,"GB2-03":64.22373469028935,"GB2-04":40.356325565953945,"GB2-05":87.02258334283259,"GB2-07":82.49880078573374,"GB2-08":67.17339011069221},"per_game_match_totals_all":{"GB2-01":{"draws":219,"losses":234,"wins":652},"GB2-02":{"draws":437,"losses":93,"wins":713},"GB2-03":{"draws":61,"losses":173,"wins":641},"GB2-04":{"draws":414,"losses":340,"wins":576},"GB2-05":{"draws":0,"losses":106,"wins":1074},"GB2-06":{"draws":9,"losses":10,"wins":205},"GB2-07":{"draws":0,"losses":116,"wins":824},"GB2-08":{"draws":53,"losses":310,"wins":1333}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":106,"wins":220},"GB2-02":{"draws":88,"losses":35,"wins":255},"GB2-03":{"draws":5,"losses":13,"wins":246},"GB2-04":{"draws":60,"losses":50,"wins":304},"GB2-05":{"draws":0,"losses":28,"wins":320},"GB2-07":{"draws":0,"losses":9,"wins":203},"GB2-08":{"draws":0,"losses":88,"wins":390}},"medium":{"GB2-01":{"draws":42,"losses":95,"wins":241},"GB2-02":{"draws":156,"losses":26,"wins":227},"GB2-03":{"draws":5,"losses":42,"wins":256},"GB2-04":{"draws":192,"losses":161,"wins":117},"GB2-05":{"draws":0,"losses":47,"wins":371},"GB2-07":{"draws":0,"losses":67,"wins":417},"GB2-08":{"draws":0,"losses":60,"wins":462}},"none":{"GB2-01":{"draws":173,"losses":33,"wins":191},"GB2-02":{"draws":193,"losses":32,"wins":231},"GB2-03":{"draws":51,"losses":118,"wins":139},"GB2-04":{"draws":162,"losses":129,"wins":155},"GB2-05":{"draws":0,"losses":31,"wins":383},"GB2-06":{"draws":9,"losses":10,"wins":205},"GB2-07":{"draws":0,"losses":40,"wins":204},"GB2-08":{"draws":53,"losses":162,"wins":481}}},"per_game_raw_elo_all":{"GB2-01":1737.7138631563128,"GB2-02":1729.2607762703094,"GB2-03":1790.272150692136,"GB2-04":1595.4725257804075,"GB2-05":2103.989908393715,"GB2-07":2033.9084368795066,"GB2-08":1893.4196705677805},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1744.8705774722998,"GB2-02":1832.472640275807,"GB2-03":2071.1826392372514,"GB2-04":1826.5336667298475,"GB2-05":2162.1358409497025,"GB2-07":2133.031338789898,"GB2-08":1938.9003236021792},"medium":{"GB2-01":1702.691576274602,"GB2-02":1688.2211683328637,"GB2-03":1870.7579146183937,"GB2-04":1432.2626624641434,"GB2-05":2027.6769598519563,"GB2-07":2037.439223289318,"GB2-08":2019.7225255654228},"none":{"GB2-01":1765.579435722036,"GB2-02":1667.0885202022573,"GB2-03":1428.8758982207626,"GB2-04":1527.6212481472317,"GB2-05":2122.1569243794847,"GB2-06":2130.3450848136745,"GB2-07":1931.2547485593036,"GB2-08":1721.63616253574}},"per_game_tracks":{"highest":{"GB2-01":60.75327500594525,"GB2-02":66.71678962770099,"GB2-03":90.4111038614959,"GB2-04":75.66030745243378,"GB2-05":90.57193620024879,"GB2-07":88.98341049342496,"GB2-08":70.56869574148102},"medium":{"GB2-01":57.84106247080217,"GB2-02":46.663704376163935,"GB2-03":71.83204982352686,"GB2-04":15.44348716732651,"GB2-05":82.28059290855728,"GB2-07":82.76813804449968,"GB2-08":76.92409146097165},"none":{"GB2-01":62.44870744872863,"GB2-02":43.90901916944084,"GB2-03":30.428050385845268,"GB2-04":29.965182078101545,"GB2-05":88.2152209196917,"GB2-06":88.50558733332528,"GB2-07":75.74485381927656,"GB2-08":54.027383129623956}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":73.73770073302038,"medium":59.93031925099359,"none":57.21331957249471},"reasoning_agg":{"highest":{"max":90.57193620024879,"mean":73.73770073302038,"min":60.75327500594525},"medium":{"max":82.76813804449968,"mean":59.93031925099359,"min":15.44348716732651},"none":{"max":88.50558733332528,"mean":57.21331957249471,"min":29.965182078101545}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":90.57193620024879,"expected_score":69.14825033599587,"reasoning_variance":16.524381160525664,"reliability_score":99.99351082580283,"uncertainty_avg":0.006489174197171289,"uncertainty_penalty":5.521137150492969},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":90.57193620024879,"expected_score":75.88813000803931,"reliability_score":99.98053247740849,"uncertainty_avg":0.01946752259151387,"uncertainty_penalty":2.1504292750189364},"medium":{"ceiling_score":82.76813804449968,"expected_score":68.3831553245651,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":8.452836073571504},"none":{"ceiling_score":88.50558733332528,"expected_score":67.77678246596028,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":10.56346289346557}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3:56eeba387b2e14bb","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.5256212,"mean":0.38805244562499996,"median":0.41839404999999996,"min":0.063446985,"recorded_attempt_count":8,"run_count":8,"total":3.1044195649999997},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23469315999999998,"mean":0.156944395,"median":0.1664265,"min":0.07192,"recorded_attempt_count":10,"run_count":8,"total":1.25555516},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1610404,"mean":0.053977109999999995,"median":0.0318207,"min":0.0217974,"recorded_attempt_count":8,"run_count":8,"total":0.43181687999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23469315999999998,"mean":0.156944395,"median":0.1664265,"min":0.07192,"recorded_attempt_count":10,"run_count":8,"total":1.2555551600000001},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1610404,"mean":0.053977109999999995,"median":0.0318207,"min":0.0217974,"recorded_attempt_count":8,"run_count":8,"total":0.43181688},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.5256212,"mean":0.38805244562499996,"median":0.41839404999999996,"min":0.063446985,"recorded_attempt_count":8,"run_count":8,"total":3.104419565}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.5256212,"mean":0.19965798354166664,"median":0.1553977,"min":0.0217974,"recorded_attempt_count":26,"run_count":24,"total":4.791791605},"codegen_latency_ms":{"attempt_count":26,"max_ms":2052448,"mean_ms":650299.2083333334,"min_ms":28293,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":2052448,"mean_ms":1191674.625,"min_ms":447340,"run_count":8},"medium":{"attempt_count":10,"max_ms":1900345,"mean_ms":621701.25,"min_ms":106081,"run_count":8},"none":{"attempt_count":8,"max_ms":420991,"mean_ms":137521.75,"min_ms":28293,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":117143,"output_mean":43372.708333333336,"output_min":2671,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":117143,"output_mean":87116.125,"output_min":13152,"run_count":8},"medium":{"attempt_count":10,"output_max":49662,"output_mean":33008.75,"output_min":15862,"run_count":8},"none":{"attempt_count":8,"output_max":33431,"output_mean":9993.25,"output_min":2671,"run_count":8}},"display_name":"GLM 5.3","economics":{"all":59.770257406879146,"highest":79.40098393480983,"medium":60.338315256130116,"none":38.05415645781677},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":26,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":26,"reconciliation_get_attempt_observations":26,"reconciliation_get_attempts":120,"total_output_tokens":1040945,"total_reasoning_output_tokens":925880,"total_visible_output_tokens":115065,"visible_token_observations":26},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"unknown_legacy","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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},"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":7,"evaluated_cells":7,"first_pass_admitted":7,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-04"],"infra_failures_excluded":1,"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-5.3","is_recent_addition":false,"last_measured_at":"2026-09-26T05:04:12Z","match_totals_all":{"draws":1330,"losses":1438,"wins":3395},"match_totals_tracks":{"highest":{"draws":197,"losses":161,"wins":1416},"medium":{"draws":379,"losses":502,"wins":1247},"none":{"draws":754,"losses":775,"wins":732}},"model_slug":"z-ai-glm-5-3","overall":{"max":97.68342390756534,"mean":59.26448521625224,"min":13.832077596500099},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":5,"overall_ranking_status":"partial","per_game":{"GB2-01":76.68418283239292,"GB2-02":42.17068661439786,"GB2-03":77.33811495492994,"GB2-05":93.22584013987411,"GB2-06":91.6059967030711,"GB2-07":97.68342390756534,"GB2-08":77.09864239143765},"per_game_all":{"GB2-01":59.77207858290904,"GB2-02":27.028465165877886,"GB2-03":57.31319762677092,"GB2-05":72.13633460992308,"GB2-06":77.76728189847162,"GB2-07":76.50457687308393,"GB2-08":47.86986709111764},"per_game_match_totals_all":{"GB2-01":{"draws":113,"losses":229,"wins":468},"GB2-02":{"draws":554,"losses":95,"wins":135},"GB2-03":{"draws":166,"losses":198,"wins":428},"GB2-04":{"draws":208,"losses":66,"wins":227},"GB2-05":{"draws":0,"losses":242,"wins":534},"GB2-06":{"draws":47,"losses":188,"wins":611},"GB2-07":{"draws":0,"losses":189,"wins":609},"GB2-08":{"draws":242,"losses":231,"wins":383}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":19,"losses":23,"wins":196},"GB2-02":{"draws":136,"losses":18,"wins":90},"GB2-03":{"draws":23,"losses":37,"wins":208},"GB2-05":{"draws":0,"losses":16,"wins":222},"GB2-06":{"draws":19,"losses":13,"wins":224},"GB2-07":{"draws":0,"losses":11,"wins":253},"GB2-08":{"draws":0,"losses":43,"wins":223}},"medium":{"GB2-01":{"draws":50,"losses":123,"wins":141},"GB2-02":{"draws":165,"losses":33,"wins":38},"GB2-03":{"draws":29,"losses":50,"wins":150},"GB2-04":{"draws":36,"losses":22,"wins":191},"GB2-05":{"draws":0,"losses":98,"wins":148},"GB2-06":{"draws":14,"losses":12,"wins":234},"GB2-07":{"draws":0,"losses":81,"wins":187},"GB2-08":{"draws":85,"losses":83,"wins":158}},"none":{"GB2-01":{"draws":44,"losses":83,"wins":131},"GB2-02":{"draws":253,"losses":44,"wins":7},"GB2-03":{"draws":114,"losses":111,"wins":70},"GB2-04":{"draws":172,"losses":44,"wins":36},"GB2-05":{"draws":0,"losses":128,"wins":164},"GB2-06":{"draws":14,"losses":163,"wins":153},"GB2-07":{"draws":0,"losses":97,"wins":169},"GB2-08":{"draws":157,"losses":105,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1724.6789172321126,"GB2-02":1544.981317948522,"GB2-03":1708.147305779091,"GB2-05":1863.6699211045325,"GB2-06":1949.722496641367,"GB2-07":1941.6527066273302,"GB2-08":1644.201081281095},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1959.9203115334649,"GB2-02":1653.8031366071834,"GB2-03":1921.443156903663,"GB2-05":2199.9629012340533,"GB2-06":2179.9807338496657,"GB2-07":2261.580188816139,"GB2-08":2021.7334942737016},"medium":{"GB2-01":1593.6235685063568,"GB2-02":1532.26139560797,"GB2-03":1738.6000853316789,"GB2-04":1774.9466538392635,"GB2-05":1839.9085863380596,"GB2-06":2177.2443491701238,"GB2-07":1777.8218576008665,"GB2-08":1687.3866173471636},"none":{"GB2-01":1620.4928716565166,"GB2-02":1448.8794216304127,"GB2-03":1464.3986751019318,"GB2-04":1458.7920892116642,"GB2-05":1551.138275741485,"GB2-06":1491.9424069043102,"GB2-07":1785.556073464985,"GB2-08":1223.4831322224204}},"per_game_tracks":{"highest":{"GB2-01":76.68418283239292,"GB2-02":42.17068661439786,"GB2-03":77.33811495492994,"GB2-05":93.22584013987411,"GB2-06":91.6059967030711,"GB2-07":97.68342390756534,"GB2-08":77.09864239143765},"medium":{"GB2-01":50.42799435291316,"GB2-02":25.082631286735698,"GB2-03":60.00864115948657,"GB2-04":68.1212799203305,"GB2-05":70.60706772290004,"GB2-06":91.45237102456348,"GB2-07":65.66210015505115,"GB2-08":51.3444364270604},"none":{"GB2-01":52.20405856342103,"GB2-02":13.832077596500099,"GB2-03":34.59283676589625,"GB2-04":19.649975790451197,"GB2-05":52.57609596699508,"GB2-06":50.243477967780315,"GB2-07":66.1682065566353,"GB2-08":15.166522454854865}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":79.40098393480983,"medium":60.338315256130116,"none":38.05415645781677},"reasoning_agg":{"highest":{"max":97.68342390756534,"mean":79.40098393480983,"min":42.17068661439786},"medium":{"max":91.45237102456348,"mean":60.338315256130116,"min":25.082631286735698},"none":{"max":66.1682065566353,"mean":38.05415645781677,"min":13.832077596500099}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":97.68342390756534,"expected_score":61.47344199260489,"reasoning_variance":41.34682747699306,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.2089567763526503},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":97.68342390756534,"expected_score":77.2673049110616,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.133679023748229},"medium":{"ceiling_score":91.45237102456348,"expected_score":64.87984117759751,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.541525921467397},"none":{"ceiling_score":66.1682065566353,"expected_score":40.48810215146783,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.4339456936510615}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-sol:0a1f83515d3cebb3","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.7965692187500001,"median":0.7419175,"min":0.6308437499999999,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":6.37255375},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"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},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.0229249999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.24740375,"mean":0.229063125,"median":0.23243875,"min":0.20046375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.832505},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.15394249999999998,"mean":0.12786562499999998,"median":0.13029000000000002,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.022925},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"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":6.372553750000001}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":1.17244375,"mean":0.3844993229166666,"median":0.23243875,"min":0.10071375,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":9.227983750000002},"codegen_output_tokens":{"attempt_count":25,"output_max":35149,"output_mean":11102.833333333334,"output_min":1851,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":35149,"output_mean":24638.75,"output_min":19522,"run_count":8},"medium":{"attempt_count":8,"output_max":6769,"output_mean":6021.5,"output_min":5176,"run_count":8},"none":{"attempt_count":8,"output_max":3391,"output_mean":2648.25,"output_min":1851,"run_count":8}},"display_name":"GPT-5.6 Sol","economics":{"all":56.43518562144288,"highest":69.83890513640115,"medium":57.437715344432895,"none":42.028936383494596},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":266468,"total_reasoning_output_tokens":151113,"total_visible_output_tokens":115355,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-sol","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"id":"gpt-5.6-sol","is_recent_addition":false,"last_measured_at":"2026-09-26T06:22:26Z","match_totals_all":{"draws":1339,"losses":2202,"wins":4911},"match_totals_tracks":{"highest":{"draws":196,"losses":442,"wins":2009},"medium":{"draws":424,"losses":735,"wins":1511},"none":{"draws":719,"losses":1025,"wins":1391}},"model_slug":"gpt-5-6-sol","overall":{"max":89.02836443424523,"mean":56.43518562144288,"min":9.878306012979403},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":64.26847738573247,"GB2-02":51.339067229848325,"GB2-03":60.98784141688205,"GB2-04":76.29901498815899,"GB2-05":72.49924027747636,"GB2-06":81.2128132284247,"GB2-07":89.02836443424523,"GB2-08":63.07642213044111},"per_game_all":{"GB2-01":60.78089267875646,"GB2-02":34.88741158748177,"GB2-03":51.57208060767226,"GB2-04":53.694688496411025,"GB2-05":65.75088754494625,"GB2-06":61.23262653526529,"GB2-07":64.7718806319012,"GB2-08":58.79101688910877},"per_game_match_totals_all":{"GB2-01":{"draws":82,"losses":295,"wins":589},"GB2-02":{"draws":544,"losses":111,"wins":337},"GB2-03":{"draws":201,"losses":287,"wins":549},"GB2-04":{"draws":368,"losses":155,"wins":486},"GB2-05":{"draws":0,"losses":338,"wins":724},"GB2-06":{"draws":46,"losses":394,"wins":683},"GB2-07":{"draws":0,"losses":359,"wins":808},"GB2-08":{"draws":98,"losses":263,"wins":735}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":103,"wins":207},"GB2-02":{"draws":108,"losses":27,"wins":197},"GB2-03":{"draws":7,"losses":59,"wins":247},"GB2-04":{"draws":44,"losses":25,"wins":239},"GB2-05":{"draws":0,"losses":85,"wins":253},"GB2-06":{"draws":29,"losses":33,"wins":272},"GB2-07":{"draws":0,"losses":30,"wins":318},"GB2-08":{"draws":0,"losses":80,"wins":276}},"medium":{"GB2-01":{"draws":72,"losses":101,"wins":145},"GB2-02":{"draws":163,"losses":29,"wins":114},"GB2-03":{"draws":38,"losses":105,"wins":180},"GB2-04":{"draws":77,"losses":26,"wins":212},"GB2-05":{"draws":0,"losses":75,"wins":243},"GB2-06":{"draws":6,"losses":186,"wins":158},"GB2-07":{"draws":0,"losses":100,"wins":276},"GB2-08":{"draws":68,"losses":113,"wins":183}},"none":{"GB2-01":{"draws":2,"losses":91,"wins":237},"GB2-02":{"draws":273,"losses":55,"wins":26},"GB2-03":{"draws":156,"losses":123,"wins":122},"GB2-04":{"draws":247,"losses":104,"wins":35},"GB2-05":{"draws":0,"losses":178,"wins":228},"GB2-06":{"draws":11,"losses":175,"wins":253},"GB2-07":{"draws":0,"losses":229,"wins":214},"GB2-08":{"draws":30,"losses":70,"wins":276}}},"per_game_raw_elo_all":{"GB2-01":1736.461664075836,"GB2-02":1598.2551726306153,"GB2-03":1643.8254871693425,"GB2-04":1677.4589893985783,"GB2-05":1758.5613474418308,"GB2-06":1672.7238635627866,"GB2-07":1760.3215455116517,"GB2-08":1782.160252468733},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1784.8099138635066,"GB2-02":1715.609120411484,"GB2-03":1745.2419658599154,"GB2-04":1825.71761543844,"GB2-05":1866.2672030772917,"GB2-06":2004.7450736106382,"GB2-07":2127.714178366969,"GB2-08":1837.6692184698486},"medium":{"GB2-01":1653.9082417126156,"GB2-02":1626.4310312500377,"GB2-03":1699.2021961126395,"GB2-04":1816.3873913598852,"GB2-05":1897.1432670181343,"GB2-06":1404.1362111621452,"GB2-07":1802.9097347908921,"GB2-08":1635.6206398658271},"none":{"GB2-01":1770.6668366513863,"GB2-02":1452.725366230324,"GB2-03":1487.0322995354722,"GB2-04":1390.2719613974093,"GB2-05":1512.273572230067,"GB2-06":1609.2903059155772,"GB2-07":1350.340723377094,"GB2-08":1873.1908990705235}},"per_game_tracks":{"highest":{"GB2-01":64.26847738573247,"GB2-02":51.339067229848325,"GB2-03":60.98784141688205,"GB2-04":76.29901498815899,"GB2-05":72.49924027747636,"GB2-06":81.2128132284247,"GB2-07":89.02836443424523,"GB2-08":63.07642213044111},"medium":{"GB2-01":54.799181182735225,"GB2-02":38.71772041218916,"GB2-03":56.704113196028175,"GB2-04":74.90674448809469,"GB2-05":74.39898479366788,"GB2-06":44.980393999976215,"GB2-07":67.57415953728002,"GB2-08":47.42042514549177},"none":{"GB2-01":63.2750194678017,"GB2-02":14.605447120407849,"GB2-03":37.02428721010656,"GB2-04":9.878306012979403,"GB2-05":50.354437563694546,"GB2-06":57.50467237739495,"GB2-07":37.713117924178334,"GB2-08":65.87620339139343}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":69.83890513640115,"medium":57.437715344432895,"none":42.028936383494596},"reasoning_agg":{"highest":{"max":89.02836443424523,"mean":69.83890513640115,"min":51.339067229848325},"medium":{"max":74.90674448809469,"mean":57.437715344432895,"min":38.71772041218916},"none":{"max":65.87620339139343,"mean":42.028936383494596,"min":9.878306012979403}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":89.02836443424523,"expected_score":56.99365883569255,"reasoning_variance":27.809968752906556,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.5584732142496662},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":89.02836443424523,"expected_score":65.51411617012266,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.32478896627849},"medium":{"ceiling_score":74.90674448809469,"expected_score":59.91398284018438,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.476267495751486},"none":{"ceiling_score":65.87620339139343,"expected_score":45.5528774967706,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.5239411132760026}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-sol:98006d193d583881","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.20679475000000003,"median":0.2051385,"min":0.185721,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.6543580000000002},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.1118895,"mean":0.07831456249999999,"median":0.0772785,"min":0.0550535,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6265165000000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.052136,"mean":0.043196000000000005,"median":0.04354475,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.345568}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.1118895,"mean":0.07831456249999999,"median":0.0772785,"min":0.0550535,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6265164999999999},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.052136,"mean":0.043196000000000005,"median":0.04354475,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.34556800000000004},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.20679475000000003,"median":0.2051385,"min":0.185721,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.6543580000000002}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.225321,"mean":0.10943510416666667,"median":0.0772785,"min":0.033231000000000004,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":24,"token_priced_attempt_count":25,"total":2.6264425},"codegen_output_tokens":{"attempt_count":25,"output_max":20604,"output_mean":8932.083333333334,"output_min":1527,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":20604,"output_mean":18742.75,"output_min":16066,"run_count":8},"medium":{"attempt_count":9,"output_max":7600,"output_mean":5670.625,"output_min":3698,"run_count":8},"none":{"attempt_count":8,"output_max":3203,"output_mean":2382.875,"output_min":1527,"run_count":8}},"display_name":"GPT-6 Sol","economics":{"all":56.13372085857782,"highest":62.8380640406884,"medium":58.39388249405774,"none":47.16921604098732},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[65536],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[65536],"total_output_tokens":214370,"total_reasoning_output_tokens":129853,"total_visible_output_tokens":84517,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":65536,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"gpt-6-sol","is_recent_addition":false,"last_measured_at":"2026-09-26T05:33:24Z","match_totals_all":{"draws":339,"losses":501,"wins":1420},"match_totals_tracks":{"highest":{"draws":67,"losses":126,"wins":541},"medium":{"draws":131,"losses":151,"wins":484},"none":{"draws":141,"losses":224,"wins":395}},"model_slug":"gpt-6-sol","overall":{"max":83.28749056558534,"mean":56.13372085857782,"min":10.681867874042462},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":7,"overall_ranking_status":"ranked","per_game":{"GB2-01":10.681867874042462,"GB2-02":42.29924871553676,"GB2-03":75.8344614658824,"GB2-04":66.10436458181071,"GB2-05":75.32347657986587,"GB2-06":83.28749056558534,"GB2-07":82.41326763629222,"GB2-08":66.76033490649137},"per_game_all":{"GB2-01":30.385520171410658,"GB2-02":32.250765765412844,"GB2-03":59.19203903247017,"GB2-04":43.62652079267473,"GB2-05":73.11705857466524,"GB2-06":72.65916292256334,"GB2-07":73.36970312770423,"GB2-08":64.46899648172135},"per_game_match_totals_all":{"GB2-01":{"draws":26,"losses":154,"wins":60},"GB2-02":{"draws":157,"losses":46,"wins":109},"GB2-03":{"draws":12,"losses":38,"wins":148},"GB2-04":{"draws":96,"losses":57,"wins":125},"GB2-05":{"draws":0,"losses":38,"wins":232},"GB2-06":{"draws":44,"losses":50,"wins":212},"GB2-07":{"draws":0,"losses":58,"wins":262},"GB2-08":{"draws":4,"losses":60,"wins":272}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":69,"wins":4},"GB2-02":{"draws":39,"losses":5,"wins":54},"GB2-03":{"draws":0,"losses":4,"wins":60},"GB2-04":{"draws":15,"losses":10,"wins":65},"GB2-05":{"draws":0,"losses":5,"wins":81},"GB2-06":{"draws":9,"losses":8,"wins":81},"GB2-07":{"draws":0,"losses":9,"wins":101},"GB2-08":{"draws":1,"losses":16,"wins":95}},"medium":{"GB2-01":{"draws":18,"losses":45,"wins":17},"GB2-02":{"draws":52,"losses":16,"wins":42},"GB2-03":{"draws":5,"losses":20,"wins":39},"GB2-04":{"draws":31,"losses":14,"wins":51},"GB2-05":{"draws":0,"losses":8,"wins":86},"GB2-06":{"draws":23,"losses":19,"wins":68},"GB2-07":{"draws":0,"losses":8,"wins":94},"GB2-08":{"draws":2,"losses":21,"wins":87}},"none":{"GB2-01":{"draws":5,"losses":40,"wins":39},"GB2-02":{"draws":66,"losses":25,"wins":13},"GB2-03":{"draws":7,"losses":14,"wins":49},"GB2-04":{"draws":50,"losses":33,"wins":9},"GB2-05":{"draws":0,"losses":25,"wins":65},"GB2-06":{"draws":12,"losses":23,"wins":63},"GB2-07":{"draws":0,"losses":41,"wins":67},"GB2-08":{"draws":1,"losses":23,"wins":90}}},"per_game_raw_elo_all":{"GB2-01":1338.4945236039737,"GB2-02":1596.5105664212813,"GB2-03":1752.414969995073,"GB2-04":1631.2982470069767,"GB2-05":1896.3169914932107,"GB2-06":1880.6760546009116,"GB2-07":1908.395162431733,"GB2-08":1872.0818832621692},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1067.2277848595288,"GB2-02":1669.3672247631073,"GB2-03":1930.6311994776556,"GB2-04":1778.4307353636148,"GB2-05":1932.3312165874324,"GB2-06":2057.4544102411373,"GB2-07":2044.3700850330902,"GB2-08":1901.615676820162},"medium":{"GB2-01":1407.1905950403973,"GB2-02":1612.7072670416555,"GB2-03":1691.6530033441315,"GB2-04":1686.8219874279168,"GB2-05":1977.069092972992,"GB2-06":1824.318358314484,"GB2-07":1992.516994406742,"GB2-08":1878.6613835543144},"none":{"GB2-01":1541.0651909119952,"GB2-02":1507.45720745908,"GB2-03":1634.9607071634316,"GB2-04":1428.6420182293984,"GB2-05":1779.5506649192084,"GB2-06":1760.2553952471137,"GB2-07":1688.2984078553666,"GB2-08":1835.9685894120314}},"per_game_tracks":{"highest":{"GB2-01":10.681867874042462,"GB2-02":42.29924871553676,"GB2-03":75.8344614658824,"GB2-04":66.10436458181071,"GB2-05":75.32347657986587,"GB2-06":83.28749056558534,"GB2-07":82.41326763629222,"GB2-08":66.76033490649137},"medium":{"GB2-01":35.35688895738572,"GB2-02":34.674280018737946,"GB2-03":53.42809062340049,"GB2-04":52.25475984178181,"GB2-05":78.2532943061813,"GB2-06":69.34643450270941,"GB2-07":78.88385679381578,"GB2-08":64.95345490844947},"none":{"GB2-01":45.11780368280379,"GB2-02":19.778768561963826,"GB2-03":48.313565008127604,"GB2-04":12.520437954431669,"GB2-05":65.77440483794854,"GB2-06":65.34356369939526,"GB2-07":58.8119849530047,"GB2-08":61.6931996302232}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":62.8380640406884,"medium":58.39388249405774,"none":47.16921604098732},"reasoning_agg":{"highest":{"max":83.28749056558534,"mean":62.8380640406884,"min":10.681867874042462},"medium":{"max":78.88385679381578,"mean":58.39388249405774,"min":34.674280018737946},"none":{"max":65.77440483794854,"mean":47.16921604098732,"min":12.520437954431669}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":83.28749056558534,"expected_score":59.1652134412654,"reasoning_variance":15.668847999701079,"reliability_score":91.97118609009345,"uncertainty_avg":8.028813909906551,"uncertainty_penalty":3.0314925826875836},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":83.28749056558534,"expected_score":59.68870016295238,"reliability_score":91.24809389560814,"uncertainty_avg":8.751906104391859,"uncertainty_penalty":-3.1493638777360218},"medium":{"ceiling_score":78.88385679381578,"expected_score":63.94359850383663,"reliability_score":92.3400860022265,"uncertainty_avg":7.659913997773495,"uncertainty_penalty":5.549716009778891},"none":{"ceiling_score":65.77440483794854,"expected_score":53.86334165700718,"reliability_score":92.3253783724457,"uncertainty_avg":7.674621627554301,"uncertainty_penalty":6.694125616019861}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-7:fb7fa57036d697f2","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":3,"cell_count":5,"cost_basis_counts":{"provider_reported":5},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.5756864,"mean":0.31644575999999996,"median":0.4788,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":3},"recorded_attempt_count":5,"run_count":5,"total":1.5822288000000002},"medium":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":7},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.4355744,"mean":0.2698891428571428,"median":0.2679664,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":6},"recorded_attempt_count":7,"run_count":7,"total":1.889224},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.143752,"mean":0.082967,"median":0.0730072,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.6637360000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":7},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.4355744,"mean":0.2698891428571428,"median":0.2679664,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":6},"recorded_attempt_count":7,"run_count":7,"total":1.8892239999999998},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.143752,"mean":0.082967,"median":0.0730072,"min":0.0533856,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.663736},"historical-provider-setting-intensive":{"admitted_cell_count":3,"cell_count":5,"cost_basis_counts":{"provider_reported":5},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.5756864,"mean":0.31644575999999996,"median":0.4788,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":3},"recorded_attempt_count":5,"run_count":5,"total":1.5822288}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":20,"cost_basis_counts":{"provider_reported":22},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.5756864,"mean":0.20675944000000004,"median":0.1363672,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":19},"recorded_attempt_count":22,"run_count":20,"total":4.1351888},"codegen_latency_ms":{"attempt_count":19,"max_ms":1681185,"mean_ms":637573.8823529412,"min_ms":107275,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":1681185,"mean_ms":1430699.0,"min_ms":1260712,"run_count":3},"medium":{"attempt_count":6,"max_ms":1184623,"mean_ms":866198.5,"min_ms":559399,"run_count":6},"none":{"attempt_count":10,"max_ms":283828,"mean_ms":168683.5,"min_ms":107275,"run_count":8}},"codegen_output_tokens":{"attempt_count":22,"output_max":117054,"output_mean":41824.8,"output_min":5971,"run_count":20},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":5,"output_max":117054,"output_mean":69484.4,"output_min":13242,"run_count":5},"medium":{"attempt_count":7,"output_max":87767,"output_mean":54559.28571428572,"output_min":5971,"run_count":7},"none":{"attempt_count":10,"output_max":23276,"output_mean":13394.875,"output_min":8421,"run_count":8}},"display_name":"Grok 4.7","economics":{"all":56.475037362500494,"highest":60.5907029247002,"medium":67.30626702195454,"none":38.865021028964016},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":22,"effective_max_output_tokens":[450000],"finish_reason_observations":19,"finish_reasons":["stop"],"indexed_attempts":22,"output_token_observations":22,"provider_post_attempt_observations":22,"provider_post_attempts":23,"reasoning_token_observations":22,"reconciliation_get_attempt_observations":22,"requested_max_output_token_observations":22,"requested_max_output_tokens":[450000],"total_output_tokens":836496,"total_reasoning_output_tokens":892618,"total_visible_output_tokens":123225,"visible_token_observations":22},"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":450000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"x-ai","provider_model":"x-ai/grok-4.7","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":6,"first_pass_admitted":6,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-06"],"infra_failures_excluded":1,"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}},"baseline":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-03"],"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.125,"model_code_failures":1,"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":3,"evaluated_cells":3,"first_pass_admitted":3,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-04","GB2-06"],"infra_failures_excluded":2,"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":"x-ai/grok-4.7","is_recent_addition":false,"last_measured_at":"2026-09-26T05:33:09Z","match_totals_all":{"draws":159,"losses":417,"wins":910},"match_totals_tracks":{"highest":{"draws":14,"losses":61,"wins":223},"medium":{"draws":18,"losses":97,"wins":437},"none":{"draws":127,"losses":259,"wins":250}},"model_slug":"x-ai-grok-4-7","overall":{"max":79.84706998284979,"mean":55.161994257350564,"min":11.031617270493685},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":8,"overall_ranking_status":"partial","per_game":{"GB2-01":56.399307086436856,"GB2-07":60.1653008402903,"GB2-08":65.20750084737345},"per_game_all":{"GB2-01":48.93906111297093,"GB2-07":56.728921177131305,"GB2-08":63.75712979739925},"per_game_match_totals_all":{"GB2-01":{"draws":42,"losses":86,"wins":126},"GB2-02":{"draws":64,"losses":19,"wins":11},"GB2-03":{"draws":6,"losses":11,"wins":47},"GB2-04":{"draws":31,"losses":54,"wins":93},"GB2-05":{"draws":0,"losses":60,"wins":104},"GB2-06":{"draws":14,"losses":15,"wins":63},"GB2-07":{"draws":0,"losses":122,"wins":208},"GB2-08":{"draws":2,"losses":50,"wins":258}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":12,"losses":20,"wins":54},"GB2-07":{"draws":0,"losses":31,"wins":75},"GB2-08":{"draws":2,"losses":10,"wins":94}},"medium":{"GB2-01":{"draws":1,"losses":23,"wins":64},"GB2-03":{"draws":6,"losses":11,"wins":47},"GB2-04":{"draws":11,"losses":8,"wins":73},"GB2-05":{"draws":0,"losses":6,"wins":82},"GB2-07":{"draws":0,"losses":37,"wins":81},"GB2-08":{"draws":0,"losses":12,"wins":90}},"none":{"GB2-01":{"draws":29,"losses":43,"wins":8},"GB2-02":{"draws":64,"losses":19,"wins":11},"GB2-04":{"draws":20,"losses":46,"wins":20},"GB2-05":{"draws":0,"losses":54,"wins":22},"GB2-06":{"draws":14,"losses":15,"wins":63},"GB2-07":{"draws":0,"losses":54,"wins":52},"GB2-08":{"draws":0,"losses":28,"wins":74}}},"per_game_raw_elo_all":{"GB2-01":1593.7463576649614,"GB2-07":1656.5299340501854,"GB2-08":1864.43897519803},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1696.5168657208674,"GB2-07":1709.092124503988,"GB2-08":1882.6393294210588},"medium":{"GB2-01":1736.028613974715,"GB2-03":1744.097357588985,"GB2-04":1810.357925990759,"GB2-05":2003.7704405270024,"GB2-07":1760.8885185843224,"GB2-08":1965.1915375099677},"none":{"GB2-01":1348.693593299301,"GB2-02":1475.2725360433346,"GB2-04":1420.3422248144257,"GB2-05":1357.2864999549527,"GB2-06":1923.4350941373648,"GB2-07":1499.6091590622455,"GB2-08":1745.4860586630634}},"per_game_tracks":{"highest":{"GB2-01":56.399307086436856,"GB2-07":60.1653008402903,"GB2-08":65.20750084737345},"medium":{"GB2-01":59.292601967171514,"GB2-03":58.34522393855917,"GB2-04":71.07115366869925,"GB2-05":79.84706998284979,"GB2-07":63.72768633792826,"GB2-08":71.55386623651924},"none":{"GB2-01":31.125274285304428,"GB2-02":14.989020277781334,"GB2-04":11.031617270493685,"GB2-05":38.98667853053844,"GB2-06":75.11875817714981,"GB2-07":46.293776353175346,"GB2-08":54.510022308305054}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":60.5907029247002,"medium":67.30626702195454,"none":37.58901282539697},"reasoning_agg":{"highest":{"max":65.20750084737345,"mean":60.5907029247002,"min":56.399307086436856},"medium":{"max":79.84706998284979,"mean":67.30626702195454,"min":58.34522393855917},"none":{"max":75.11875817714981,"mean":37.58901282539697,"min":11.031617270493685}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":79.84706998284979,"expected_score":58.714563746470084,"reasoning_variance":29.71725419655757,"reliability_score":93.57895529750526,"uncertainty_avg":6.421044702494746,"uncertainty_penalty":3.55256948911952},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":65.20750084737345,"expected_score":57.910699972540534,"reliability_score":93.65690811784796,"uncertainty_avg":6.343091882152031,"uncertainty_penalty":-2.6800029521596684},"medium":{"ceiling_score":79.84706998284979,"expected_score":74.87786461948409,"reliability_score":91.25564520143554,"uncertainty_avg":8.744354798564453,"uncertainty_penalty":7.571597597529546},"none":{"ceiling_score":75.11875817714981,"expected_score":43.85799105427169,"reliability_score":91.33696268163699,"uncertainty_avg":8.66303731836301,"uncertainty_penalty":6.2689782288747224}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-fable-5:13ae1db461acc087","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":1.47056875,"median":1.411685,"min":0.98262,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":11.76455},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.30885}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.73774,"mean":0.5233875,"median":0.47084000000000004,"min":0.34112,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":4.1871},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.35085,"mean":0.28860625,"median":0.282885,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.30885},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":1.47056875,"median":1.411685,"min":0.98262,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":11.764549999999998}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":2.14955,"mean":0.7608541666666667,"median":0.47084000000000004,"min":0.22654,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":18.2605},"codegen_output_tokens":{"attempt_count":24,"output_max":40578,"output_mean":12704.708333333334,"output_min":2179,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":40578,"output_mean":26899.0,"output_min":17366,"run_count":8},"medium":{"attempt_count":8,"output_max":12403,"output_mean":7955.375,"output_min":4188,"run_count":8},"none":{"attempt_count":8,"output_max":4224,"output_mean":3259.75,"output_min":2179,"run_count":8}},"display_name":"Claude Fable 5","economics":{"all":54.63313476954879,"highest":65.13623015137362,"medium":53.57537339316034,"none":45.187800764112396},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[128000],"finish_reason_observations":24,"finish_reasons":["end_turn"],"indexed_attempts":24,"output_token_observations":24,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":24,"reconciliation_get_attempt_observations":24,"requested_max_output_token_observations":24,"requested_max_output_tokens":[128000],"total_output_tokens":304913,"total_reasoning_output_tokens":206534,"total_visible_output_tokens":98379,"visible_token_observations":24},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"claude-fable-5","is_recent_addition":false,"last_measured_at":"2026-09-26T06:33:04Z","match_totals_all":{"draws":1249,"losses":1669,"wins":3279},"match_totals_tracks":{"highest":{"draws":317,"losses":457,"wins":1243},"medium":{"draws":395,"losses":554,"wins":1063},"none":{"draws":537,"losses":658,"wins":973}},"model_slug":"claude-fable-5","overall":{"max":88.38916443390323,"mean":54.63313476954878,"min":4.493356423490963},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-01":73.61219615766171,"GB2-02":58.14238860910562,"GB2-03":72.74449999990529,"GB2-04":88.38916443390323,"GB2-05":52.321705316196045,"GB2-06":84.21510524225893,"GB2-07":60.28507978183338,"GB2-08":31.37970167012484},"per_game_all":{"GB2-01":63.34465939324938,"GB2-02":32.60390472478839,"GB2-03":39.29571773737632,"GB2-04":40.15727164065928,"GB2-05":62.237562983897355,"GB2-06":77.02005049488633,"GB2-07":61.64854338139927,"GB2-08":60.757367800133956},"per_game_match_totals_all":{"GB2-01":{"draws":62,"losses":195,"wins":447},"GB2-02":{"draws":401,"losses":82,"wins":221},"GB2-03":{"draws":254,"losses":251,"wins":209},"GB2-04":{"draws":351,"losses":177,"wins":271},"GB2-05":{"draws":0,"losses":329,"wins":477},"GB2-06":{"draws":56,"losses":133,"wins":541},"GB2-07":{"draws":0,"losses":349,"wins":567},"GB2-08":{"draws":125,"losses":153,"wins":546}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":36,"wins":186},"GB2-02":{"draws":79,"losses":20,"wins":137},"GB2-03":{"draws":73,"losses":23,"wins":146},"GB2-04":{"draws":27,"losses":29,"wins":185},"GB2-05":{"draws":0,"losses":139,"wins":157},"GB2-06":{"draws":14,"losses":31,"wins":197},"GB2-07":{"draws":0,"losses":102,"wins":164},"GB2-08":{"draws":124,"losses":77,"wins":71}},"medium":{"GB2-01":{"draws":25,"losses":78,"wins":133},"GB2-02":{"draws":145,"losses":28,"wins":67},"GB2-03":{"draws":66,"losses":144,"wins":22},"GB2-04":{"draws":131,"losses":55,"wins":60},"GB2-05":{"draws":0,"losses":96,"wins":160},"GB2-06":{"draws":28,"losses":41,"wins":179},"GB2-07":{"draws":0,"losses":89,"wins":177},"GB2-08":{"draws":0,"losses":23,"wins":265}},"none":{"GB2-01":{"draws":37,"losses":81,"wins":128},"GB2-02":{"draws":177,"losses":34,"wins":17},"GB2-03":{"draws":115,"losses":84,"wins":41},"GB2-04":{"draws":193,"losses":93,"wins":26},"GB2-05":{"draws":0,"losses":94,"wins":160},"GB2-06":{"draws":14,"losses":61,"wins":165},"GB2-07":{"draws":0,"losses":158,"wins":226},"GB2-08":{"draws":1,"losses":53,"wins":210}}},"per_game_raw_elo_all":{"GB2-01":1775.7169247097352,"GB2-02":1586.0238228413639,"GB2-03":1517.1854135164267,"GB2-04":1591.9309331509082,"GB2-05":1705.78806866723,"GB2-06":1939.0392182431697,"GB2-07":1715.9371116851762,"GB2-08":1810.7083968145864},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1918.3659092889625,"GB2-02":1768.2321376305474,"GB2-03":1873.7209132666478,"GB2-04":1907.4959813961932,"GB2-05":1546.9356435195423,"GB2-06":2058.2766686123414,"GB2-07":1696.7111275471811,"GB2-08":1432.1181360704918},"medium":{"GB2-01":1702.1797790225423,"GB2-02":1585.1931675443645,"GB2-03":1289.9826257189723,"GB2-04":1510.8553371546875,"GB2-05":1787.5546073902776,"GB2-06":1927.020956699484,"GB2-07":1795.9646582442433,"GB2-08":2083.6860082580997},"none":{"GB2-01":1706.6050858177005,"GB2-02":1404.64616334918,"GB2-03":1387.8527015636598,"GB2-04":1357.4414809018433,"GB2-05":1782.8739550918694,"GB2-06":1831.8200294176834,"GB2-07":1655.1355492641044,"GB2-08":1916.3210461151682}},"per_game_tracks":{"highest":{"GB2-01":73.61219615766171,"GB2-02":58.14238860910562,"GB2-03":72.74449999990529,"GB2-04":88.38916443390323,"GB2-05":52.321705316196045,"GB2-06":84.21510524225893,"GB2-07":60.28507978183338,"GB2-08":31.37970167012484},"medium":{"GB2-01":58.03160934481367,"GB2-02":32.528765715421166,"GB2-03":17.962661834227674,"GB2-04":27.58929406458364,"GB2-05":67.345755890244,"GB2-06":76.3090844854146,"GB2-07":66.85744130341878,"GB2-08":81.97837450715917},"none":{"GB2-01":58.390172677272766,"GB2-02":7.140559849838393,"GB2-03":27.17999137799601,"GB2-04":4.493356423490963,"GB2-05":67.045227745252,"GB2-06":70.53596175698547,"GB2-07":57.80310905894567,"GB2-08":68.91402722311787}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":65.13623015137362,"medium":53.57537339316034,"none":45.187800764112396},"reasoning_agg":{"highest":{"max":88.38916443390323,"mean":65.13623015137362,"min":31.37970167012484},"medium":{"max":81.97837450715917,"mean":53.57537339316034,"min":17.962661834227674},"none":{"max":70.53596175698547,"mean":45.187800764112396,"min":4.493356423490963}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":88.38916443390323,"expected_score":54.980863951933216,"reasoning_variance":19.94842938726123,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.34772918238443395},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":88.38916443390323,"expected_score":60.51462643972147,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.621603711652156},"medium":{"ceiling_score":81.97837450715917,"expected_score":55.53563458955523,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.9602611963948888},"none":{"ceiling_score":70.53596175698547,"expected_score":48.89233082652293,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.7045300624105337}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-6:de845d6d61a8ca84","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.23409475,"median":0.240558,"min":0.184404,"recorded_attempt_count":9,"run_count":8,"total":1.8727580000000001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.179588,"mean":0.12726625,"median":0.12371399999999999,"min":0.092184,"recorded_attempt_count":10,"run_count":8,"total":1.01813},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.041774,"mean":0.03185375,"median":0.031432,"min":0.027072,"recorded_attempt_count":8,"run_count":8,"total":0.25483}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.179588,"mean":0.12726625,"median":0.12371399999999999,"min":0.092184,"recorded_attempt_count":10,"run_count":8,"total":1.01813},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.041774,"mean":0.03185375,"median":0.031432,"min":0.027072,"recorded_attempt_count":8,"run_count":8,"total":0.25483},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.23409475,"median":0.240558,"min":0.184404,"recorded_attempt_count":9,"run_count":8,"total":1.872758}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":27},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28029,"mean":0.13107158333333335,"median":0.12371399999999999,"min":0.027072,"recorded_attempt_count":27,"run_count":24,"total":3.1457180000000005},"codegen_latency_ms":{"attempt_count":27,"max_ms":669574,"mean_ms":286694.0416666667,"min_ms":31621,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":669574,"mean_ms":551119.125,"min_ms":414817,"run_count":8},"medium":{"attempt_count":10,"max_ms":376458,"mean_ms":270365.25,"min_ms":196147,"run_count":8},"none":{"attempt_count":8,"max_ms":49571,"mean_ms":38597.75,"min_ms":31621,"run_count":8}},"codegen_output_tokens":{"attempt_count":27,"output_max":43739,"output_mean":18621.333333333332,"output_min":1925,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":43739,"output_mean":35745.125,"output_min":27954,"run_count":8},"medium":{"attempt_count":10,"output_max":24183,"output_mean":17614.25,"output_min":12541,"run_count":8},"none":{"attempt_count":8,"output_max":3323,"output_mean":2504.625,"output_min":1925,"run_count":8}},"display_name":"Grok 4.6","economics":{"all":48.05298078590767,"highest":52.77710893167817,"medium":58.373520707791855,"none":33.00831271825298},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"reconciliation_get_attempts":128,"total_output_tokens":446912,"total_reasoning_output_tokens":311255,"total_visible_output_tokens":135657,"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":"x-ai","provider_model":"x-ai/grok-4.6","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"id":"x-ai/grok-4.6","is_recent_addition":false,"last_measured_at":"2026-09-26T06:59:40Z","match_totals_all":{"draws":1875,"losses":1957,"wins":2777},"match_totals_tracks":{"highest":{"draws":580,"losses":622,"wins":1049},"medium":{"draws":422,"losses":454,"wins":1096},"none":{"draws":873,"losses":881,"wins":632}},"model_slug":"x-ai-grok-4-6","overall":{"max":81.71055442696685,"mean":48.052980785907664,"min":12.881742968455264},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-01":42.49728250159177,"GB2-02":62.00350433866778,"GB2-03":36.041937156995054,"GB2-04":35.979212310524815,"GB2-05":81.71055442696685,"GB2-06":61.573232881711505,"GB2-07":72.11152601375798,"GB2-08":30.299621823209698},"per_game_all":{"GB2-01":47.00374223877724,"GB2-02":34.107218497362496,"GB2-03":41.038093062624355,"GB2-04":30.77117612296658,"GB2-05":71.65706998129846,"GB2-06":52.75771470820779,"GB2-07":64.12055779793332,"GB2-08":42.968273878091175},"per_game_match_totals_all":{"GB2-01":{"draws":276,"losses":253,"wins":319},"GB2-02":{"draws":407,"losses":99,"wins":221},"GB2-03":{"draws":356,"losses":198,"wins":236},"GB2-04":{"draws":441,"losses":210,"wins":227},"GB2-05":{"draws":0,"losses":226,"wins":550},"GB2-06":{"draws":56,"losses":393,"wins":323},"GB2-07":{"draws":0,"losses":313,"wins":573},"GB2-08":{"draws":339,"losses":265,"wins":328}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":171,"losses":74,"wins":75},"GB2-02":{"draws":37,"losses":26,"wins":166},"GB2-03":{"draws":81,"losses":113,"wins":122},"GB2-04":{"draws":141,"losses":83,"wins":104},"GB2-05":{"draws":0,"losses":32,"wins":208},"GB2-06":{"draws":25,"losses":116,"wins":113},"GB2-07":{"draws":0,"losses":77,"wins":189},"GB2-08":{"draws":125,"losses":101,"wins":72}},"medium":{"GB2-01":{"draws":70,"losses":81,"wins":87},"GB2-02":{"draws":165,"losses":38,"wins":45},"GB2-03":{"draws":61,"losses":58,"wins":113},"GB2-04":{"draws":101,"losses":49,"wins":98},"GB2-05":{"draws":0,"losses":45,"wins":193},"GB2-06":{"draws":25,"losses":49,"wins":168},"GB2-07":{"draws":0,"losses":81,"wins":183},"GB2-08":{"draws":0,"losses":53,"wins":209}},"none":{"GB2-01":{"draws":35,"losses":98,"wins":157},"GB2-02":{"draws":205,"losses":35,"wins":10},"GB2-03":{"draws":214,"losses":27,"wins":1},"GB2-04":{"draws":199,"losses":78,"wins":25},"GB2-05":{"draws":0,"losses":149,"wins":149},"GB2-06":{"draws":6,"losses":228,"wins":42},"GB2-07":{"draws":0,"losses":155,"wins":201},"GB2-08":{"draws":214,"losses":111,"wins":47}}},"per_game_raw_elo_all":{"GB2-01":1547.6326355561735,"GB2-02":1596.3507519597806,"GB2-03":1534.6689456265303,"GB2-04":1529.608289882802,"GB2-05":1856.0761613215634,"GB2-06":1536.513064626545,"GB2-07":1753.5608049834902,"GB2-08":1580.12904420178},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1483.7793572967885,"GB2-02":1796.184063312853,"GB2-03":1479.0709629459723,"GB2-04":1562.1539467719574,"GB2-05":2016.7656472238368,"GB2-06":1682.656177274989,"GB2-07":1875.3100284540096,"GB2-08":1417.1187481578122},"medium":{"GB2-01":1567.4698964670868,"GB2-02":1541.3275656059245,"GB2-03":1698.7770162709437,"GB2-04":1614.1720786490882,"GB2-05":1969.7915579212736,"GB2-06":1882.3135930922363,"GB2-07":1844.4642402698223,"GB2-08":1931.7685728360664},"none":{"GB2-01":1591.648652904645,"GB2-02":1451.540626960565,"GB2-03":1426.1588576626746,"GB2-04":1412.4988442273602,"GB2-05":1581.6712788195796,"GB2-06":1044.5694235124092,"GB2-07":1540.9081462266392,"GB2-08":1391.4998116114623}},"per_game_tracks":{"highest":{"GB2-01":42.49728250159177,"GB2-02":62.00350433866778,"GB2-03":36.041937156995054,"GB2-04":35.979212310524815,"GB2-05":81.71055442696685,"GB2-06":61.573232881711505,"GB2-07":72.11152601375798,"GB2-08":30.299621823209698},"medium":{"GB2-01":48.29471183335914,"GB2-02":26.441610714839133,"GB2-03":56.2908393049293,"GB2-04":43.45257308991965,"GB2-05":78.7493883467507,"GB2-06":73.59101700850034,"GB2-07":70.06287690019776,"GB2-08":70.10514846383883},"none":{"GB2-01":50.21923238138081,"GB2-02":13.876540438580571,"GB2-03":30.781502725948716,"GB2-04":12.881742968455264,"GB2-05":54.511267170177824,"GB2-06":23.108894234411515,"GB2-07":50.187270479844194,"GB2-08":28.500051347224986}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.77710893167817,"medium":58.373520707791855,"none":33.00831271825298},"reasoning_agg":{"highest":{"max":81.71055442696685,"mean":52.77710893167817,"min":30.299621823209698},"medium":{"max":78.7493883467507,"mean":58.373520707791855,"min":26.441610714839133},"none":{"max":54.511267170177824,"mean":33.00831271825298,"min":12.881742968455264}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":81.71055442696685,"expected_score":47.38103430926338,"reasoning_variance":25.365207989538874,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.6719464766442869},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":81.71055442696685,"expected_score":45.478927842345556,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.298181089332616},"medium":{"ceiling_score":78.7493883467507,"expected_score":62.31940909726549,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.9458883894736374},"none":{"ceiling_score":54.511267170177824,"expected_score":34.34476598817907,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.3364532699260891}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-pro:d87db7f47c3dd584","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":5,"cell_count":5,"cost_basis_counts":{"provider_reported":5},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1085880432,"mean":0.08096321663999999,"median":0.07468254,"min":0.048483795,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":5},"recorded_attempt_count":5,"run_count":5,"total":0.4048160832},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01198425,"mean":0.00718913625,"median":0.0061211025,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.05751309}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":5,"cost_basis_counts":{"provider_reported":5},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1085880432,"mean":0.08096321663999999,"median":0.07468254,"min":0.048483795,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":5},"recorded_attempt_count":5,"run_count":5,"total":0.4048160832},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01198425,"mean":0.00718913625,"median":0.0061211025,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.057513089999999996}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":13,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.1085880432,"mean":0.03556378255384615,"median":0.010081125,"min":0.005105595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":15},"recorded_attempt_count":15,"run_count":13,"total":0.4623291731999999},"codegen_latency_ms":{"attempt_count":15,"max_ms":2725508,"mean_ms":682983.6153846154,"min_ms":33029,"run_count":13},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":5,"max_ms":2725508,"mean_ms":1690249.4,"min_ms":1007453,"run_count":5},"none":{"attempt_count":10,"max_ms":84396,"mean_ms":53442.5,"min_ms":33029,"run_count":8}},"codegen_output_tokens":{"attempt_count":15,"output_max":124769,"output_mean":36754.692307692305,"output_min":2214,"run_count":13},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":5,"output_max":124769,"output_mean":90077.2,"output_min":52107,"run_count":5},"none":{"attempt_count":10,"output_max":6088,"output_mean":3428.125,"output_min":2214,"run_count":8}},"display_name":"MiMo-V2.6-Pro","economics":{"medium":59.39077570112681,"none":35.34389944599556},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":15,"effective_max_output_tokens":[131072],"finish_reason_observations":15,"finish_reasons":["stop"],"indexed_attempts":15,"output_token_observations":15,"provider_post_attempt_observations":15,"provider_post_attempts":16,"reasoning_token_observations":15,"reconciliation_get_attempt_observations":15,"requested_max_output_token_observations":15,"requested_max_output_tokens":[131072],"total_output_tokens":477811,"total_reasoning_output_tokens":423370,"total_visible_output_tokens":54441,"visible_token_observations":15},"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":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":5,"first_pass_admitted":5,"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}},"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":"xiaomi/mimo-v2.6-pro","is_recent_addition":false,"last_measured_at":"2026-09-26T05:14:32Z","match_totals_all":{"draws":298,"losses":399,"wins":559},"match_totals_tracks":{"medium":{"draws":115,"losses":55,"wins":318},"none":{"draws":183,"losses":344,"wins":241}},"model_slug":"xiaomi-mimo-v2-6-pro","overall":{"max":77.50294541114951,"mean":47.36733757356119,"min":4.5082501228042835},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":11,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":54,"losses":71,"wins":37},"GB2-02":{"draws":109,"losses":36,"wins":55},"GB2-03":{"draws":13,"losses":35,"wins":20},"GB2-04":{"draws":112,"losses":19,"wins":57},"GB2-05":{"draws":0,"losses":65,"wins":27},"GB2-06":{"draws":10,"losses":72,"wins":130},"GB2-07":{"draws":0,"losses":71,"wins":39},"GB2-08":{"draws":0,"losses":30,"wins":194}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":17,"losses":31,"wins":28},"GB2-02":{"draws":40,"losses":5,"wins":55},"GB2-04":{"draws":54,"losses":6,"wins":38},"GB2-06":{"draws":4,"losses":7,"wins":91},"GB2-08":{"draws":0,"losses":6,"wins":106}},"none":{"GB2-01":{"draws":37,"losses":40,"wins":9},"GB2-02":{"draws":69,"losses":31,"wins":0},"GB2-03":{"draws":13,"losses":35,"wins":20},"GB2-04":{"draws":58,"losses":13,"wins":19},"GB2-05":{"draws":0,"losses":65,"wins":27},"GB2-06":{"draws":6,"losses":65,"wins":39},"GB2-07":{"draws":0,"losses":71,"wins":39},"GB2-08":{"draws":0,"losses":24,"wins":88}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1490.3101566554815,"GB2-02":1724.6243809014807,"GB2-04":1688.7277671209645,"GB2-06":1926.9640593655313,"GB2-08":2040.094437534735},"none":{"GB2-01":1388.5412755080495,"GB2-02":1399.2262608684266,"GB2-03":1437.0139222406397,"GB2-04":1531.3754818380596,"GB2-05":1326.9189346051687,"GB2-06":1500.4418196516035,"GB2-07":1382.2495697401266,"GB2-08":1821.267345550081}},"per_game_tracks":{"medium":{"GB2-01":41.28722402399608,"GB2-02":50.096880260768124,"GB2-04":52.610331126030445,"GB2-06":75.45649768368993,"GB2-08":77.50294541114951},"none":{"GB2-01":34.12066053365314,"GB2-02":4.5082501228042835,"GB2-03":29.690216218433648,"GB2-04":28.209004129779423,"GB2-05":37.33498756572203,"GB2-06":49.79180400180289,"GB2-07":38.56902988674707,"GB2-08":60.527243109022024}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":59.39077570112681,"none":35.34389944599556},"reasoning_agg":{"medium":{"max":77.50294541114951,"mean":59.39077570112681,"min":41.28722402399608},"none":{"max":60.527243109022024,"mean":35.34389944599556,"min":4.5082501228042835}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":77.50294541114951,"reasoning_variance":24.046876255131252},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":77.50294541114951,"expected_score":64.85363594063463,"reliability_score":93.09269083386529,"uncertainty_avg":6.907309166134709,"uncertainty_penalty":5.462860239507819},"none":{"ceiling_score":60.527243109022024,"expected_score":39.49794316007087,"reliability_score":92.5294897047099,"uncertainty_avg":7.470510295290094,"uncertainty_penalty":4.154043714075307}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4:c444884bfba7584b","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.15224},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.266995},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.4120425,"mean":0.283374375,"median":0.26543625,"min":0.2124125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.266995},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.179715,"mean":0.09608781250000001,"median":0.08063500000000001,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.7687025000000001},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":1.51903,"median":1.4938600000000002,"min":1.088255,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":12.152239999999999}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":27},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":2.2530275,"mean":0.6328307291666667,"median":0.26543625,"min":0.0656625,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":15.187937500000002},"codegen_output_tokens":{"attempt_count":27,"output_max":146534,"output_mean":40675.041666666664,"output_min":3180,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":146534,"output_mean":99672.5,"output_min":71368,"run_count":8},"medium":{"attempt_count":8,"output_max":26272,"output_mean":17600.375,"output_min":12941,"run_count":8},"none":{"attempt_count":10,"output_max":8643,"output_mean":4752.25,"output_min":3180,"run_count":8}},"display_name":"GPT-5.4","economics":{"all":49.641968332527945,"highest":61.98389944331557,"medium":44.0793909076606,"none":35.3357783819767},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"total_output_tokens":976201,"total_reasoning_output_tokens":819733,"total_visible_output_tokens":156468,"visible_token_observations":27},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.4","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-02"],"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.125,"model_code_failures":1,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"gpt-5.4","is_recent_addition":false,"last_measured_at":"2026-09-26T06:22:57Z","match_totals_all":{"draws":2214,"losses":2326,"wins":3535},"match_totals_tracks":{"highest":{"draws":379,"losses":493,"wins":1543},"medium":{"draws":904,"losses":798,"wins":1128},"none":{"draws":931,"losses":1035,"wins":864}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":46.4546754571148,"min":2.0650714063351248},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-01":86.55897744574543,"GB2-03":26.828756753128754,"GB2-04":36.57094809628825,"GB2-05":82.31399825868931,"GB2-06":74.45149619886398,"GB2-07":76.79039298080251,"GB2-08":50.37272636969076},"per_game_all":{"GB2-01":82.74523839425729,"GB2-03":26.353374449524683,"GB2-04":16.217724285101678,"GB2-05":67.9198011108627,"GB2-06":70.24200141981528,"GB2-07":49.26279944526001,"GB2-08":34.75283922287401},"per_game_match_totals_all":{"GB2-01":{"draws":35,"losses":85,"wins":842},"GB2-02":{"draws":522,"losses":88,"wins":27},"GB2-03":{"draws":495,"losses":370,"wins":218},"GB2-04":{"draws":535,"losses":294,"wins":174},"GB2-05":{"draws":0,"losses":280,"wins":700},"GB2-06":{"draws":72,"losses":241,"wins":705},"GB2-07":{"draws":0,"losses":579,"wins":587},"GB2-08":{"draws":555,"losses":389,"wins":282}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":16,"wins":294},"GB2-03":{"draws":138,"losses":146,"wins":111},"GB2-04":{"draws":166,"losses":48,"wins":104},"GB2-05":{"draws":0,"losses":34,"wins":296},"GB2-06":{"draws":27,"losses":56,"wins":255},"GB2-07":{"draws":0,"losses":64,"wins":286},"GB2-08":{"draws":42,"losses":129,"wins":197}},"medium":{"GB2-01":{"draws":5,"losses":4,"wins":307},"GB2-02":{"draws":267,"losses":50,"wins":20},"GB2-03":{"draws":189,"losses":111,"wins":70},"GB2-04":{"draws":159,"losses":119,"wins":32},"GB2-05":{"draws":0,"losses":98,"wins":220},"GB2-06":{"draws":23,"losses":64,"wins":253},"GB2-07":{"draws":0,"losses":232,"wins":156},"GB2-08":{"draws":261,"losses":120,"wins":70}},"none":{"GB2-01":{"draws":24,"losses":65,"wins":241},"GB2-02":{"draws":255,"losses":38,"wins":7},"GB2-03":{"draws":168,"losses":113,"wins":37},"GB2-04":{"draws":210,"losses":127,"wins":38},"GB2-05":{"draws":0,"losses":148,"wins":184},"GB2-06":{"draws":22,"losses":121,"wins":197},"GB2-07":{"draws":0,"losses":283,"wins":145},"GB2-08":{"draws":252,"losses":140,"wins":15}}},"per_game_raw_elo_all":{"GB2-01":2040.1394470756184,"GB2-03":1374.3578485497474,"GB2-04":1433.1700772342438,"GB2-05":1793.830961732892,"GB2-06":1822.8674838649083,"GB2-07":1526.0913286071518,"GB2-08":1471.2043345039967},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2093.019902422547,"GB2-03":1378.4410521432442,"GB2-04":1566.3546993919815,"GB2-05":2022.5799507387826,"GB2-06":1892.6304163174875,"GB2-07":1942.8394772921415,"GB2-08":1673.56380344235},"medium":{"GB2-01":2278.825931725217,"GB2-02":1441.2442787426126,"GB2-03":1411.89411645307,"GB2-04":1341.6830864711928,"GB2-05":1762.661012335324,"GB2-06":1891.1322011094626,"GB2-07":1327.0713985926327,"GB2-08":1426.3679003269972},"none":{"GB2-01":1748.5725070790916,"GB2-02":1448.832561906253,"GB2-03":1332.7383770529277,"GB2-04":1391.4724458395567,"GB2-05":1596.2519221245693,"GB2-06":1684.8398341677748,"GB2-07":1308.3631099366814,"GB2-08":1313.681299742643}},"per_game_tracks":{"highest":{"GB2-01":86.55897744574543,"GB2-03":26.828756753128754,"GB2-04":36.57094809628825,"GB2-05":82.31399825868931,"GB2-06":74.45149619886398,"GB2-07":76.79039298080251,"GB2-08":50.37272636969076},"medium":{"GB2-01":100.0,"GB2-02":12.92305393909728,"GB2-03":29.90282146528025,"GB2-04":2.0650714063351248,"GB2-05":65.94082554184169,"GB2-06":74.36489099861892,"GB2-07":36.086344480969686,"GB2-08":31.35211942914186},"none":{"GB2-01":61.67673773702644,"GB2-02":13.804261498123136,"GB2-03":22.328545130165047,"GB2-04":10.017153352681662,"GB2-05":55.504579532057114,"GB2-06":61.90961706196294,"GB2-07":34.91166087400782,"GB2-08":22.533671869789416}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":59.94885708170712,"medium":44.0793909076606,"none":35.3357783819767},"reasoning_agg":{"highest":{"max":86.55897744574543,"mean":59.94885708170712,"min":26.828756753128754},"medium":{"max":100.0,"mean":44.0793909076606,"min":2.0650714063351248},"none":{"max":61.90961706196294,"mean":35.3357783819767,"min":10.017153352681662}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":48.55550247004931,"reasoning_variance":24.613078699730416,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.1008270129345092},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":86.55897744574543,"expected_score":55.84783038353344,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.101026698173676},"medium":{"ceiling_score":100.0,"expected_score":44.380104356266315,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.3007134486057126},"none":{"ceiling_score":61.90961706196294,"expected_score":37.703763280802015,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.3679848988253127}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flash:b7f0d7586457fa6c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.014901165624999999,"median":0.013297725,"min":0.0073485,"recorded_attempt_count":9,"run_count":8,"total":0.119209325},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01518705,"mean":0.00578608125,"median":0.0045066875,"min":0.0032555,"recorded_attempt_count":8,"run_count":8,"total":0.04628865},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0140393,"mean":0.0037309874999999996,"median":0.0024275875,"min":0.001111625,"recorded_attempt_count":11,"run_count":8,"total":0.0298479}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01518705,"mean":0.00578608125,"median":0.0045066875,"min":0.0032555,"recorded_attempt_count":8,"run_count":8,"total":0.04628865},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0140393,"mean":0.0037309874999999996,"median":0.0024275875,"min":0.001111625,"recorded_attempt_count":11,"run_count":8,"total":0.029847900000000004},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.014901165624999999,"median":0.013297725,"min":0.0073485,"recorded_attempt_count":9,"run_count":8,"total":0.11920932499999999}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02871725,"mean":0.008139411458333334,"median":0.005035225,"min":0.001111625,"recorded_attempt_count":28,"run_count":24,"total":0.19534587499999997},"codegen_latency_ms":{"attempt_count":28,"max_ms":1214245,"mean_ms":417506.625,"min_ms":32605,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":1196482,"mean_ms":748510.375,"min_ms":448704,"run_count":8},"medium":{"attempt_count":8,"max_ms":672648,"mean_ms":296260.625,"min_ms":146516,"run_count":8},"none":{"attempt_count":11,"max_ms":1214245,"mean_ms":207748.875,"min_ms":32605,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":65809,"output_mean":27118.375,"output_min":2294,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":65809,"output_mean":50033.0,"output_min":27276,"run_count":8},"medium":{"attempt_count":8,"output_max":58608,"output_mean":20833.875,"output_min":10904,"run_count":8},"none":{"attempt_count":11,"output_max":54017,"output_mean":10488.25,"output_min":2294,"run_count":8}},"display_name":"GLM 5.3 Flash","economics":{"all":46.42997354268896,"highest":50.12396170067102,"medium":54.041999357459765,"none":35.123959569936105},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":134,"total_output_tokens":650841,"total_reasoning_output_tokens":555865,"total_visible_output_tokens":94976,"visible_token_observations":28},"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-5.3-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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},"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":"z-ai/glm-5.3-flash","is_recent_addition":false,"last_measured_at":"2026-09-26T06:08:30Z","match_totals_all":{"draws":1687,"losses":2132,"wins":2610},"match_totals_tracks":{"highest":{"draws":440,"losses":664,"wins":1002},"medium":{"draws":538,"losses":654,"wins":957},"none":{"draws":709,"losses":814,"wins":651}},"model_slug":"z-ai-glm-5-3-flash","overall":{"max":74.15726553520925,"mean":46.42997354268897,"min":9.389615782509672},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":13,"overall_ranking_status":"ranked","per_game":{"GB2-01":56.39320833754935,"GB2-02":41.306743703926635,"GB2-03":60.609751214619,"GB2-04":63.4949115682178,"GB2-05":74.15726553520925,"GB2-06":21.26225571940009,"GB2-07":65.28807392103528,"GB2-08":18.47948360541068},"per_game_all":{"GB2-01":51.229044728299364,"GB2-02":24.73398999892223,"GB2-03":52.13825943724873,"GB2-04":57.75655481741395,"GB2-05":56.471683128839516,"GB2-06":45.88259441363342,"GB2-07":65.85912747553782,"GB2-08":17.368534341616705},"per_game_match_totals_all":{"GB2-01":{"draws":163,"losses":302,"wins":381},"GB2-02":{"draws":516,"losses":98,"wins":132},"GB2-03":{"draws":196,"losses":206,"wins":333},"GB2-04":{"draws":203,"losses":143,"wins":412},"GB2-05":{"draws":0,"losses":375,"wins":443},"GB2-06":{"draws":62,"losses":422,"wins":348},"GB2-07":{"draws":0,"losses":267,"wins":537},"GB2-08":{"draws":547,"losses":319,"wins":24}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":103,"wins":203},"GB2-02":{"draws":122,"losses":25,"wins":91},"GB2-03":{"draws":54,"losses":63,"wins":133},"GB2-04":{"draws":52,"losses":35,"wins":159},"GB2-05":{"draws":0,"losses":73,"wins":177},"GB2-06":{"draws":9,"losses":185,"wins":48},"GB2-07":{"draws":0,"losses":95,"wins":189},"GB2-08":{"draws":201,"losses":85,"wins":2}},"medium":{"GB2-01":{"draws":7,"losses":92,"wins":137},"GB2-02":{"draws":191,"losses":45,"wins":24},"GB2-03":{"draws":61,"losses":56,"wins":120},"GB2-04":{"draws":55,"losses":61,"wins":152},"GB2-05":{"draws":0,"losses":175,"wins":151},"GB2-06":{"draws":22,"losses":52,"wins":178},"GB2-07":{"draws":0,"losses":77,"wins":179},"GB2-08":{"draws":202,"losses":96,"wins":16}},"none":{"GB2-01":{"draws":154,"losses":107,"wins":41},"GB2-02":{"draws":203,"losses":28,"wins":17},"GB2-03":{"draws":81,"losses":87,"wins":80},"GB2-04":{"draws":96,"losses":47,"wins":101},"GB2-05":{"draws":0,"losses":127,"wins":115},"GB2-06":{"draws":31,"losses":185,"wins":122},"GB2-07":{"draws":0,"losses":95,"wins":169},"GB2-08":{"draws":144,"losses":138,"wins":6}}},"per_game_raw_elo_all":{"GB2-01":1606.0654820681023,"GB2-02":1529.1175045859939,"GB2-03":1653.790537900609,"GB2-04":1707.2082057681655,"GB2-05":1614.0513339491251,"GB2-06":1421.9062268686523,"GB2-07":1780.8145570357128,"GB2-08":1250.495352226607},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1676.3032613921735,"GB2-02":1647.955354857597,"GB2-03":1743.8838635810887,"GB2-04":1744.9386478697452,"GB2-05":1896.1520772946446,"GB2-06":1015.6105337813365,"GB2-07":1771.4789674453016,"GB2-08":1265.1468165959675},"medium":{"GB2-01":1757.6923971344202,"GB2-02":1493.667893856095,"GB2-03":1714.703810262849,"GB2-04":1795.060755450437,"GB2-05":1575.9776366781075,"GB2-06":1889.0595538908663,"GB2-07":1825.815320893354,"GB2-08":1338.366329274454},"none":{"GB2-01":1384.2007876777138,"GB2-02":1445.7292650442894,"GB2-03":1502.7839398578903,"GB2-04":1581.625213984314,"GB2-05":1370.0242878746226,"GB2-06":1361.0485929337547,"GB2-07":1745.1493827684824,"GB2-08":1147.9729108093998}},"per_game_tracks":{"highest":{"GB2-01":56.39320833754935,"GB2-02":41.306743703926635,"GB2-03":60.609751214619,"GB2-04":63.4949115682178,"GB2-05":74.15726553520925,"GB2-06":21.26225571940009,"GB2-07":65.28807392103528,"GB2-08":18.47948360541068},"medium":{"GB2-01":62.04733668632007,"GB2-02":19.84704134726959,"GB2-03":57.8100657522967,"GB2-04":71.34609692564236,"GB2-05":54.21685323043211,"GB2-06":74.0292432209175,"GB2-07":68.80285405987014,"GB2-08":24.23650363692976},"none":{"GB2-01":35.24658916102867,"GB2-02":13.048184945570464,"GB2-03":37.994961344830465,"GB2-04":38.428655958381675,"GB2-05":41.0409306208772,"GB2-06":42.35628430058266,"GB2-07":63.486454445708056,"GB2-08":9.389615782509672}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.12396170067102,"medium":54.041999357459765,"none":35.123959569936105},"reasoning_agg":{"highest":{"max":74.15726553520925,"mean":50.12396170067102,"min":18.47948360541068},"medium":{"max":74.0292432209175,"mean":54.041999357459765,"min":19.84704134726959},"none":{"max":63.486454445708056,"mean":35.123959569936105,"min":9.389615782509672}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":74.15726553520925,"expected_score":45.42868032316353,"reasoning_variance":18.91803978752366,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0012932195254365},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.15726553520925,"expected_score":42.284916032362005,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.839045668309012},"medium":{"ceiling_score":74.0292432209175,"expected_score":56.77820505888778,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.7362057014280126},"none":{"ceiling_score":63.486454445708056,"expected_score":37.22291987824084,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.098960308304733}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-8-flash:2a6a0471e29241b9","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.14318721034763582,"median":0.1303062996496891,"min":0.10133749410144509,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1454976827810865},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.12249677080183623,"mean":0.07182689102312519,"median":0.06440174762499168,"min":0.044067488277453076,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5746151281850016},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.041197616649628,"mean":0.031941679879238995,"median":0.03128326283110872,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2555334390339119}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.12249677080183623,"mean":0.07182689102312519,"median":0.06440174762499168,"min":0.044067488277453076,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.5746151281850015},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.041197616649628,"mean":0.031941679879238995,"median":0.03128326283110872,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.25553343903391196},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.14318721034763582,"median":0.1303062996496891,"min":0.10133749410144509,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1454976827810865}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.2764612177973556,"mean":0.08231859375,"median":0.06440174762499168,"min":0.026892580852245062,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":1.97564625},"codegen_output_tokens":{"attempt_count":25,"output_max":73160,"output_mean":20095.833333333332,"output_min":1712,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":73160,"output_mean":40784.875,"output_min":28671,"run_count":8},"medium":{"attempt_count":8,"output_max":31721,"output_mean":16792.0,"output_min":5265,"run_count":8},"none":{"attempt_count":8,"output_max":3473,"output_mean":2710.625,"output_min":1712,"run_count":8}},"display_name":"Gemini 3.8 Flash","economics":{"all":46.03841059213041,"highest":50.49677098450981,"medium":46.54975430128731,"none":41.068706490594124},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":482300,"total_reasoning_output_tokens":300593,"total_visible_output_tokens":181707,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"google","provider_model":"google/gemini-3.8-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125}},"id":"google/gemini-3.8-flash","is_recent_addition":false,"last_measured_at":"2026-09-26T05:41:30Z","match_totals_all":{"draws":1593,"losses":2077,"wins":2890},"match_totals_tracks":{"highest":{"draws":346,"losses":669,"wins":1113},"medium":{"draws":667,"losses":657,"wins":873},"none":{"draws":580,"losses":751,"wins":904}},"model_slug":"google-gemini-3-8-flash","overall":{"max":83.574890587405,"mean":46.03841059213041,"min":8.558752133756157},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":14,"overall_ranking_status":"ranked","per_game":{"GB2-01":39.083630560940236,"GB2-02":41.214691037717465,"GB2-03":59.59281095635534,"GB2-04":20.034524104182815,"GB2-05":64.34365742447741,"GB2-06":83.574890587405,"GB2-07":61.54147464837552,"GB2-08":34.588488556624654},"per_game_all":{"GB2-01":48.037906575820784,"GB2-02":21.33744404739859,"GB2-03":55.54431062175765,"GB2-04":24.182810117961864,"GB2-05":54.56254816532828,"GB2-06":74.58015326052085,"GB2-07":51.20430935450245,"GB2-08":38.85780259375283},"per_game_match_totals_all":{"GB2-01":{"draws":193,"losses":299,"wins":416},"GB2-02":{"draws":507,"losses":95,"wins":111},"GB2-03":{"draws":158,"losses":180,"wins":426},"GB2-04":{"draws":326,"losses":243,"wins":192},"GB2-05":{"draws":0,"losses":379,"wins":423},"GB2-06":{"draws":54,"losses":166,"wins":512},"GB2-07":{"draws":0,"losses":424,"wins":500},"GB2-08":{"draws":355,"losses":291,"wins":310}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":140,"wins":161},"GB2-02":{"draws":100,"losses":35,"wins":107},"GB2-03":{"draws":23,"losses":64,"wins":144},"GB2-04":{"draws":36,"losses":110,"wins":93},"GB2-05":{"draws":0,"losses":97,"wins":147},"GB2-06":{"draws":22,"losses":35,"wins":183},"GB2-07":{"draws":0,"losses":101,"wins":169},"GB2-08":{"draws":144,"losses":87,"wins":109}},"medium":{"GB2-01":{"draws":33,"losses":73,"wins":136},"GB2-02":{"draws":203,"losses":28,"wins":2},"GB2-03":{"draws":62,"losses":19,"wins":159},"GB2-04":{"draws":160,"losses":61,"wins":61},"GB2-05":{"draws":0,"losses":126,"wins":114},"GB2-06":{"draws":17,"losses":54,"wins":177},"GB2-07":{"draws":0,"losses":167,"wins":203},"GB2-08":{"draws":192,"losses":129,"wins":21}},"none":{"GB2-01":{"draws":139,"losses":86,"wins":119},"GB2-02":{"draws":204,"losses":32,"wins":2},"GB2-03":{"draws":73,"losses":97,"wins":123},"GB2-04":{"draws":130,"losses":72,"wins":38},"GB2-05":{"draws":0,"losses":156,"wins":162},"GB2-06":{"draws":15,"losses":77,"wins":152},"GB2-07":{"draws":0,"losses":156,"wins":128},"GB2-08":{"draws":19,"losses":75,"wins":180}}},"per_game_raw_elo_all":{"GB2-01":1561.196650241971,"GB2-02":1505.440794201473,"GB2-03":1689.7286168908388,"GB2-04":1488.3169222205124,"GB2-05":1583.926377041547,"GB2-06":1898.5930664770133,"GB2-07":1558.016600597346,"GB2-08":1526.7663189265638},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1436.5204825595924,"GB2-02":1647.0844730994882,"GB2-03":1734.0510593713882,"GB2-04":1461.9712203659112,"GB2-05":1740.4258692465185,"GB2-06":2047.7792692137073,"GB2-07":1715.5034354217098,"GB2-08":1470.9334570831224},"medium":{"GB2-01":1688.8656784138386,"GB2-02":1455.0280052025128,"GB2-03":1803.728818461449,"GB2-04":1566.6160501454326,"GB2-05":1484.8722134991467,"GB2-06":1859.1931391263004,"GB2-07":1604.8452636017628,"GB2-08":1328.9248715053864},"none":{"GB2-01":1558.2037897524815,"GB2-02":1414.209904302418,"GB2-03":1531.4059728396796,"GB2-04":1436.3634961501932,"GB2-05":1526.481048378976,"GB2-06":1788.806791091032,"GB2-07":1353.701102768566,"GB2-08":1780.4406281911824}},"per_game_tracks":{"highest":{"GB2-01":39.083630560940236,"GB2-02":41.214691037717465,"GB2-03":59.59281095635534,"GB2-04":20.034524104182815,"GB2-05":64.34365742447741,"GB2-06":83.574890587405,"GB2-07":61.54147464837552,"GB2-08":34.588488556624654},"medium":{"GB2-01":57.09183019900822,"GB2-02":14.238888970722154,"GB2-03":66.1721448485027,"GB2-04":36.39907957338031,"GB2-05":48.2575209538515,"GB2-06":72.21385759493866,"GB2-07":54.44775720527418,"GB2-08":23.576955064620734},"none":{"GB2-01":47.93825896751389,"GB2-02":8.558752133756157,"GB2-03":40.867976060414925,"GB2-04":16.114826676322465,"GB2-05":51.086466117655924,"GB2-06":67.95171159921891,"GB2-07":37.62369620985766,"GB2-08":58.4079641600131}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.49677098450981,"medium":46.54975430128731,"none":41.068706490594124},"reasoning_agg":{"highest":{"max":83.574890587405,"mean":50.49677098450981,"min":20.034524104182815},"medium":{"max":72.21385759493866,"mean":46.54975430128731,"min":14.238888970722154},"none":{"max":67.95171159921891,"mean":41.068706490594124,"min":8.558752133756157}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":83.574890587405,"expected_score":45.812825603918185,"reasoning_variance":9.428064493915684,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.22558498821222628},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":83.574890587405,"expected_score":43.802966345270725,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.693804639239083},"medium":{"ceiling_score":72.21385759493866,"expected_score":48.961169062552976,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.411414761265668},"none":{"ceiling_score":67.95171159921891,"expected_score":44.674341403930846,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.605634913336722}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-4-5:8eb1badb0c39eeb6","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":8,"total":0.5947036}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.0992248,"mean":0.07433795,"median":0.0774068,"min":0.0424244,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":8,"total":0.5947036},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"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},"cost_is_complete":false,"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":1.6998544000000002},"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":45.35291132735226,"highest":50.502503878316034,"medium":48.770858244486476,"none":36.785371859254276},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T05:00:47Z","match_totals_all":{"draws":2027,"losses":2575,"wins":3797},"match_totals_tracks":{"highest":{"draws":595,"losses":891,"wins":1725},"medium":{"draws":452,"losses":515,"wins":907},"none":{"draws":980,"losses":1169,"wins":1165}},"model_slug":"x-ai-grok-4-5","overall":{"max":79.30694776449921,"mean":45.35291132735227,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":74.37027635530953,"GB2-02":31.525609067395425,"GB2-03":24.00812983606703,"GB2-04":22.20149225802884,"GB2-05":70.06062948660403,"GB2-06":50.90947540682076,"GB2-07":51.63747085180339,"GB2-08":79.30694776449921},"per_game_all":{"GB2-01":65.37055407899611,"GB2-02":23.386773859915593,"GB2-03":20.504158809879854,"GB2-04":15.900832009125835,"GB2-05":61.77128776909765,"GB2-06":47.17930548568918,"GB2-07":57.52719239130332,"GB2-08":71.18318621481053},"per_game_match_totals_all":{"GB2-01":{"draws":352,"losses":186,"wins":521},"GB2-02":{"draws":666,"losses":151,"wins":180},"GB2-03":{"draws":303,"losses":411,"wins":161},"GB2-04":{"draws":613,"losses":219,"wins":146},"GB2-05":{"draws":0,"losses":368,"wins":603},"GB2-06":{"draws":85,"losses":635,"wins":553},"GB2-07":{"draws":0,"losses":445,"wins":707},"GB2-08":{"draws":8,"losses":160,"wins":926}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":75,"losses":36,"wins":277},"GB2-02":{"draws":185,"losses":56,"wins":115},"GB2-03":{"draws":151,"losses":118,"wins":88},"GB2-04":{"draws":157,"losses":114,"wins":93},"GB2-05":{"draws":0,"losses":93,"wins":269},"GB2-06":{"draws":23,"losses":227,"wins":242},"GB2-07":{"draws":0,"losses":201,"wins":281},"GB2-08":{"draws":4,"losses":46,"wins":360}},"medium":{"GB2-01":{"draws":12,"losses":29,"wins":143},"GB2-02":{"draws":180,"losses":42,"wins":46},"GB2-03":{"draws":62,"losses":40,"wins":52},"GB2-04":{"draws":175,"losses":41,"wins":26},"GB2-05":{"draws":0,"losses":69,"wins":135},"GB2-06":{"draws":19,"losses":156,"wins":111},"GB2-07":{"draws":0,"losses":111,"wins":159},"GB2-08":{"draws":4,"losses":27,"wins":235}},"none":{"GB2-01":{"draws":265,"losses":121,"wins":101},"GB2-02":{"draws":301,"losses":53,"wins":19},"GB2-03":{"draws":90,"losses":253,"wins":21},"GB2-04":{"draws":281,"losses":64,"wins":27},"GB2-05":{"draws":0,"losses":206,"wins":199},"GB2-06":{"draws":43,"losses":252,"wins":200},"GB2-07":{"draws":0,"losses":133,"wins":267},"GB2-08":{"draws":0,"losses":87,"wins":331}}},"per_game_raw_elo_all":{"GB2-01":1800.2479493832077,"GB2-02":1516.2548038644145,"GB2-03":1315.6198984674966,"GB2-04":1431.6381741657806,"GB2-05":1696.8986938322314,"GB2-06":1439.0678887609608,"GB2-07":1651.4075123670802,"GB2-08":1942.2505516107176},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1922.3402834053038,"GB2-02":1573.436912838674,"GB2-03":1349.397172670748,"GB2-04":1471.215634234893,"GB2-05":1826.763543158645,"GB2-06":1499.0021962426056,"GB2-07":1559.838955949782,"GB2-08":2045.4508315223948},"medium":{"GB2-01":1915.1414884426438,"GB2-02":1551.6562815375682,"GB2-03":1504.3310246257054,"GB2-04":1445.0654725486918,"GB2-05":1730.8772649350046,"GB2-06":1404.9717383713223,"GB2-07":1608.8446219005466,"GB2-08":1943.3473273465145},"none":{"GB2-01":1563.2620763016757,"GB2-02":1423.6712172170005,"GB2-03":1093.1314981060361,"GB2-04":1378.6334157137571,"GB2-05":1533.0552734030446,"GB2-06":1413.2297316689544,"GB2-07":1785.5389592509127,"GB2-08":1837.9534959632438}},"per_game_tracks":{"highest":{"GB2-01":74.37027635530953,"GB2-02":31.525609067395425,"GB2-03":24.00812983606703,"GB2-04":22.20149225802884,"GB2-05":70.06062948660403,"GB2-06":50.90947540682076,"GB2-07":51.63747085180339,"GB2-08":79.30694776449921},"medium":{"GB2-01":73.18922824439844,"GB2-02":28.023247677952952,"GB2-03":37.50434659357253,"GB2-04":17.46590513640475,"GB2-05":63.59328174336568,"GB2-06":44.89433859451996,"GB2-07":54.4787507633783,"GB2-08":71.01776720229921},"none":{"GB2-01":48.55215763728038,"GB2-02":10.611464834398403,"GB2-03":0.0,"GB2-04":8.03509863294391,"GB2-05":51.65995207732323,"GB2-06":45.73410245572681,"GB2-07":66.46535555872826,"GB2-08":63.22484367763318}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.502503878316034,"medium":48.770858244486476,"none":36.785371859254276},"reasoning_agg":{"highest":{"max":79.30694776449921,"mean":50.502503878316034,"min":22.20149225802884},"medium":{"max":73.18922824439844,"mean":48.770858244486476,"min":17.46590513640475},"none":{"max":66.46535555872826,"mean":36.785371859254276,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":79.30694776449921,"expected_score":43.79190417739239,"reasoning_variance":13.717132019061758,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.5610071499598774},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":79.30694776449921,"expected_score":43.13473765377268,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.367766224543352},"medium":{"ceiling_score":73.18922824439844,"expected_score":50.02689673414048,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.2560384896540029},"none":{"ceiling_score":66.46535555872826,"expected_score":38.214078144264015,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.4287062850097385}}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy4-preview:099a318abd9bb600","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.969381525},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.086615744},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.127518125}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.135826968,"median":0.126875313,"min":0.097439089,"recorded_attempt_count":10,"run_count":8,"total":1.086615744},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.028804516000000002,"mean":0.015939765625,"median":0.0150484685,"min":0.009391185,"recorded_attempt_count":9,"run_count":8,"total":0.12751812499999998},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.151385561,"mean":0.12117269062500001,"median":0.1216224665,"min":0.099918984,"recorded_attempt_count":9,"run_count":8,"total":0.969381525}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.190258393,"mean":0.09097980808333334,"median":0.1119999555,"min":0.009391185,"recorded_attempt_count":28,"run_count":24,"total":2.183515394},"codegen_latency_ms":{"attempt_count":28,"max_ms":1122981,"mean_ms":579882.5416666666,"min_ms":29109,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":995043,"mean_ms":822481.25,"min_ms":674828,"run_count":8},"medium":{"attempt_count":10,"max_ms":1122981,"mean_ms":860540.0,"min_ms":640692,"run_count":8},"none":{"attempt_count":9,"max_ms":99413,"mean_ms":56626.375,"min_ms":29109,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":69581,"output_mean":33844.916666666664,"output_min":1323,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":57331,"output_mean":47325.375,"output_min":39792,"run_count":8},"medium":{"attempt_count":10,"output_max":69581,"output_mean":50814.0,"output_min":36329,"run_count":8},"none":{"attempt_count":9,"output_max":6014,"output_mean":3395.375,"output_min":1323,"run_count":8}},"display_name":"Hy4 Preview","economics":{"all":46.6853753017164,"highest":51.96392844677858,"medium":50.01593138772429,"none":35.60469170450339},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"reconciliation_get_attempts":131,"total_output_tokens":812278,"total_reasoning_output_tokens":673611,"total_visible_output_tokens":138667,"visible_token_observations":28},"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/hy4-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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},"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":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":"tencent/hy4-preview","is_recent_addition":false,"last_measured_at":"2026-09-26T04:41:07Z","match_totals_all":{"draws":1673,"losses":2052,"wins":2618},"match_totals_tracks":{"highest":{"draws":615,"losses":599,"wins":980},"medium":{"draws":320,"losses":650,"wins":979},"none":{"draws":738,"losses":803,"wins":659}},"model_slug":"tencent-hy4-preview","overall":{"max":81.36481019561054,"mean":45.31414632990798,"min":10.545293774252402},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":16,"overall_ranking_status":"ranked","per_game":{"GB2-01":48.06083073469045,"GB2-02":59.722305814029006,"GB2-03":50.8279845604309,"GB2-04":32.33943446414669,"GB2-05":58.8500104703462,"GB2-06":77.78463136428853,"GB2-07":65.22931236711183,"GB2-08":22.89691779918504},"per_game_all":{"GB2-01":44.53365505529943,"GB2-03":43.709527185858654,"GB2-04":19.420220997956154,"GB2-05":54.957824510695076,"GB2-06":61.698861552553836,"GB2-07":60.28298157410854,"GB2-08":42.194556235543104},"per_game_match_totals_all":{"GB2-01":{"draws":227,"losses":376,"wins":331},"GB2-02":{"draws":287,"losses":45,"wins":178},"GB2-03":{"draws":266,"losses":192,"wins":247},"GB2-04":{"draws":443,"losses":160,"wins":109},"GB2-05":{"draws":0,"losses":417,"wins":477},"GB2-06":{"draws":38,"losses":311,"wins":499},"GB2-07":{"draws":0,"losses":328,"wins":510},"GB2-08":{"draws":412,"losses":223,"wins":267}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":165,"losses":74,"wins":83},"GB2-02":{"draws":75,"losses":19,"wins":172},"GB2-03":{"draws":23,"losses":69,"wins":140},"GB2-04":{"draws":119,"losses":53,"wins":76},"GB2-05":{"draws":0,"losses":100,"wins":142},"GB2-06":{"draws":17,"losses":54,"wins":175},"GB2-07":{"draws":0,"losses":115,"wins":177},"GB2-08":{"draws":216,"losses":115,"wins":15}},"medium":{"GB2-01":{"draws":15,"losses":143,"wins":138},"GB2-03":{"draws":151,"losses":53,"wins":27},"GB2-04":{"draws":146,"losses":68,"wins":16},"GB2-05":{"draws":0,"losses":150,"wins":168},"GB2-06":{"draws":8,"losses":141,"wins":197},"GB2-07":{"draws":0,"losses":67,"wins":199},"GB2-08":{"draws":0,"losses":28,"wins":234}},"none":{"GB2-01":{"draws":47,"losses":159,"wins":110},"GB2-02":{"draws":212,"losses":26,"wins":6},"GB2-03":{"draws":92,"losses":70,"wins":80},"GB2-04":{"draws":178,"losses":39,"wins":17},"GB2-05":{"draws":0,"losses":167,"wins":167},"GB2-06":{"draws":13,"losses":116,"wins":127},"GB2-07":{"draws":0,"losses":146,"wins":134},"GB2-08":{"draws":196,"losses":80,"wins":18}}},"per_game_raw_elo_all":{"GB2-01":1512.248340521699,"GB2-03":1564.4265057666432,"GB2-04":1458.0664934008025,"GB2-05":1588.9421614539642,"GB2-06":1683.6465596011712,"GB2-07":1696.1031224915657,"GB2-08":1570.461425914241},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1560.6195168262802,"GB2-02":1778.0059283813298,"GB2-03":1640.5121958876048,"GB2-04":1541.7210121358046,"GB2-05":1653.1834411461452,"GB2-06":1951.562346562994,"GB2-07":1770.265865183308,"GB2-08":1320.0339341673903},"medium":{"GB2-01":1490.0146567912957,"GB2-03":1416.1643433753093,"GB2-04":1404.9474476919663,"GB2-05":1543.7345418109614,"GB2-06":1668.575330639523,"GB2-07":1869.886400337924,"GB2-08":2076.912437263148},"none":{"GB2-01":1486.1108479475206,"GB2-02":1428.070462816653,"GB2-03":1636.6029780370154,"GB2-04":1427.5310203746371,"GB2-05":1569.908501404786,"GB2-06":1430.802001600997,"GB2-07":1448.1571019534651,"GB2-08":1314.4379063121849}},"per_game_tracks":{"highest":{"GB2-01":48.06083073469045,"GB2-02":59.722305814029006,"GB2-03":50.8279845604309,"GB2-04":32.33943446414669,"GB2-05":58.8500104703462,"GB2-06":77.78463136428853,"GB2-07":65.22931236711183,"GB2-08":22.89691779918504},"medium":{"GB2-01":42.88435173213014,"GB2-03":29.78805152747751,"GB2-04":11.211335546967721,"GB2-05":52.17161148082868,"GB2-06":60.93897454443418,"GB2-07":71.75238468662124,"GB2-08":81.36481019561054},"none":{"GB2-01":42.655782699077704,"GB2-02":10.545293774252402,"GB2-03":50.51254546966753,"GB2-04":14.709892982754058,"GB2-05":53.85185158091035,"GB2-06":46.3729787489388,"GB2-07":43.86724766859256,"GB2-08":22.321940711833715}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":51.96392844677858,"medium":48.373818838441984,"none":35.60469170450339},"reasoning_agg":{"highest":{"max":77.78463136428853,"mean":51.96392844677858,"min":22.89691779918504},"medium":{"max":81.36481019561054,"mean":48.373818838441984,"min":11.211335546967721},"none":{"max":53.85185158091035,"mean":35.60469170450339,"min":10.545293774252402}},"reasoning_labels":{"highest":"High","medium":"Low","none":"None"},"reasoning_settings":{"balanced":"low","baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":81.36481019561054,"expected_score":45.29050981119592,"reasoning_variance":16.359236742275193,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.02363651871205974},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.78463136428853,"expected_score":44.981701230188534,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.982227216590047},"medium":{"ceiling_score":81.36481019561054,"expected_score":51.78552017750061,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.4117013390586237},"none":{"ceiling_score":53.85185158091035,"expected_score":37.82163108247314,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.2169393779697515}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-3:ccaff938efc69b13","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":7},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.273243,"mean":0.18666160714285715,"median":0.20966,"min":0.0,"recorded_attempt_count":7,"run_count":7,"total":1.3066312500000001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.07423675,"mean":0.05217515625,"median":0.050446875,"min":0.04135875,"recorded_attempt_count":8,"run_count":8,"total":0.41740125000000006},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.043892749999999994,"mean":0.023888718750000003,"median":0.020423875,"min":0.017614,"recorded_attempt_count":9,"run_count":8,"total":0.19110974999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.07423675,"mean":0.05217515625,"median":0.050446875,"min":0.04135875,"recorded_attempt_count":8,"run_count":8,"total":0.41740125000000006},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.043892749999999994,"mean":0.023888718750000003,"median":0.020423875,"min":0.017614,"recorded_attempt_count":9,"run_count":8,"total":0.19110975000000002},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":7,"cost_basis_counts":{"provider_reported":7},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.273243,"mean":0.18666160714285715,"median":0.20966,"min":0.0,"recorded_attempt_count":7,"run_count":7,"total":1.30663125}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":23,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.273243,"mean":0.0832670543478261,"median":0.04626,"min":0.0,"recorded_attempt_count":24,"run_count":23,"total":1.9151422499999997},"codegen_latency_ms":{"attempt_count":23,"max_ms":386315,"mean_ms":129456.54545454546,"min_ms":18724,"run_count":22},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":6,"max_ms":386315,"mean_ms":316724.3333333333,"min_ms":225323,"run_count":6},"medium":{"attempt_count":8,"max_ms":148027,"mean_ms":92816.75,"min_ms":70623,"run_count":8},"none":{"attempt_count":9,"max_ms":39588,"mean_ms":25645.5,"min_ms":18724,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":62136,"output_mean":17319.304347826088,"output_min":242,"run_count":23},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":7,"output_max":62136,"output_mean":41969.57142857143,"output_min":242,"run_count":7},"medium":{"attempt_count":8,"output_max":15366,"output_mean":10008.75,"output_min":7655,"run_count":8},"none":{"attempt_count":9,"output_max":5638,"output_mean":3060.875,"output_min":2043,"run_count":8}},"display_name":"Muse Spark 1.3","economics":{"all":45.948882401215634,"highest":54.882251851065455,"medium":50.4562992456396,"none":30.578712397154373},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":24,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":25,"reconciliation_get_attempts":116,"total_output_tokens":398344,"total_reasoning_output_tokens":309189,"total_visible_output_tokens":88913,"visible_token_observations":23},"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-1.3","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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":6,"evaluated_cells":6,"first_pass_admitted":6,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-04","GB2-05"],"infra_failures_excluded":2,"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-1.3","is_recent_addition":false,"last_measured_at":"2026-09-26T06:57:54Z","match_totals_all":{"draws":1363,"losses":1933,"wins":2575},"match_totals_tracks":{"highest":{"draws":305,"losses":390,"wins":824},"medium":{"draws":333,"losses":691,"wins":1118},"none":{"draws":725,"losses":852,"wins":633}},"model_slug":"meta-muse-spark-1-3","overall":{"max":77.66129754772706,"mean":45.30575449795314,"min":12.765364629463813},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":17,"overall_ranking_status":"partial","per_game":{"GB2-01":68.64790008339557,"GB2-02":16.243050175095092,"GB2-03":48.46642933531042,"GB2-06":77.66129754772706,"GB2-07":54.734493398686354,"GB2-08":63.54034056617819},"per_game_all":{"GB2-01":50.81283239199839,"GB2-02":19.35458031313635,"GB2-03":40.27360643560662,"GB2-06":67.51912489520778,"GB2-07":47.70629189360304,"GB2-08":50.02685847774165},"per_game_match_totals_all":{"GB2-01":{"draws":72,"losses":278,"wins":376},"GB2-02":{"draws":552,"losses":111,"wins":85},"GB2-03":{"draws":208,"losses":259,"wins":330},"GB2-04":{"draws":261,"losses":118,"wins":125},"GB2-05":{"draws":0,"losses":300,"wins":278},"GB2-06":{"draws":48,"losses":230,"wins":520},"GB2-07":{"draws":0,"losses":433,"wins":437},"GB2-08":{"draws":222,"losses":204,"wins":424}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":59,"wins":176},"GB2-02":{"draws":194,"losses":42,"wins":22},"GB2-03":{"draws":86,"losses":56,"wins":95},"GB2-06":{"draws":23,"losses":37,"wins":192},"GB2-07":{"draws":0,"losses":138,"wins":134},"GB2-08":{"draws":1,"losses":58,"wins":205}},"medium":{"GB2-01":{"draws":0,"losses":82,"wins":164},"GB2-02":{"draws":158,"losses":30,"wins":46},"GB2-03":{"draws":45,"losses":101,"wins":106},"GB2-04":{"draws":103,"losses":57,"wins":92},"GB2-05":{"draws":0,"losses":136,"wins":138},"GB2-06":{"draws":12,"losses":58,"wins":196},"GB2-07":{"draws":0,"losses":156,"wins":176},"GB2-08":{"draws":15,"losses":71,"wins":200}},"none":{"GB2-01":{"draws":71,"losses":137,"wins":36},"GB2-02":{"draws":200,"losses":39,"wins":17},"GB2-03":{"draws":77,"losses":102,"wins":129},"GB2-04":{"draws":158,"losses":61,"wins":33},"GB2-05":{"draws":0,"losses":164,"wins":140},"GB2-06":{"draws":13,"losses":135,"wins":132},"GB2-07":{"draws":0,"losses":139,"wins":127},"GB2-08":{"draws":206,"losses":75,"wins":19}}},"per_game_raw_elo_all":{"GB2-01":1602.0691281592647,"GB2-02":1490.6932173128243,"GB2-03":1526.348548494109,"GB2-06":1780.5834076296458,"GB2-07":1505.807210262484,"GB2-08":1672.0284133677699},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1848.9372760876906,"GB2-02":1468.0390860533712,"GB2-03":1615.0479850532922,"GB2-06":1949.216005507177,"GB2-07":1612.6175904698177,"GB2-08":1847.0509680090342},"medium":{"GB2-01":1730.616026244056,"GB2-02":1524.8884161130236,"GB2-03":1476.724172043227,"GB2-04":1570.0856922463872,"GB2-05":1591.3689645443906,"GB2-06":1947.4834502111535,"GB2-07":1553.1270631978446,"GB2-08":1846.7909125107149},"none":{"GB2-01":1226.6540821460476,"GB2-02":1479.1521497720785,"GB2-03":1487.2734883858077,"GB2-04":1413.908511498883,"GB2-05":1445.2926496412001,"GB2-06":1445.0507671706064,"GB2-07":1351.67697711979,"GB2-08":1322.2433595835614}},"per_game_tracks":{"highest":{"GB2-01":68.64790008339557,"GB2-02":16.243050175095092,"GB2-03":48.46642933531042,"GB2-06":77.66129754772706,"GB2-07":54.734493398686354,"GB2-08":63.54034056617819},"medium":{"GB2-01":60.1271001226884,"GB2-02":24.034211381026175,"GB2-03":35.57048499272204,"GB2-04":36.72110114731334,"GB2-05":55.059036722419954,"GB2-06":77.59703409424492,"GB2-07":50.94674337192192,"GB2-08":63.59468213278004},"none":{"GB2-01":23.663496969911208,"GB2-02":17.786479383287784,"GB2-03":36.783904978787405,"GB2-04":12.765364629463813,"GB2-05":45.94821852766587,"GB2-06":47.29904304365135,"GB2-07":37.43763891020083,"GB2-08":22.945552734266702}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.882251851065455,"medium":50.4562992456396,"none":30.578712397154373},"reasoning_agg":{"highest":{"max":77.66129754772706,"mean":54.882251851065455,"min":16.243050175095092},"medium":{"max":77.59703409424492,"mean":50.4562992456396,"min":24.034211381026175},"none":{"max":47.29904304365135,"mean":30.578712397154373,"min":12.765364629463813}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":77.66129754772706,"expected_score":45.449024277244625,"reasoning_variance":24.303539453911082,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.14326977929148654},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.66129754772706,"expected_score":49.32004059949765,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.562211251567803},"medium":{"ceiling_score":77.59703409424492,"expected_score":52.52878748978728,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.072488244147678},"none":{"ceiling_score":47.29904304365135,"expected_score":32.41564086906266,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.8369284719082906}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-8:890495dbb6c94c7c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.34174499999999997,"mean":0.217940625,"median":0.19638,"min":0.14813,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":1.743525},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"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},"cost_is_complete":false,"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":7.449890000000001}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":false,"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":10.456240000000003},"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":45.11286416375878,"highest":60.10529092425467,"medium":37.47206434695934,"none":35.724612829101446},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T05:33:30Z","match_totals_all":{"draws":1305,"losses":1358,"wins":2209},"match_totals_tracks":{"highest":{"draws":208,"losses":310,"wins":990},"medium":{"draws":679,"losses":501,"wins":626},"none":{"draws":418,"losses":547,"wins":593}},"model_slug":"claude-opus-4-8","overall":{"max":77.2968555369974,"mean":43.38523361246347,"min":9.375632668651434},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":18,"overall_ranking_status":"ranked","per_game":{"GB2-01":62.246071636380556,"GB2-02":55.13307379115065,"GB2-04":34.85712071940729,"GB2-05":52.44277934918639,"GB2-06":77.2968555369974,"GB2-07":68.20377730883659,"GB2-08":70.55735812782373},"per_game_all":{"GB2-01":48.398690998596,"GB2-02":25.196157847295893,"GB2-04":20.427524033600086,"GB2-05":43.32336794301896,"GB2-06":65.81116214865352,"GB2-07":60.41452842466288,"GB2-08":52.21861775048412},"per_game_match_totals_all":{"GB2-01":{"draws":117,"losses":181,"wins":304},"GB2-02":{"draws":476,"losses":77,"wins":145},"GB2-03":{"draws":82,"losses":55,"wins":23},"GB2-04":{"draws":437,"losses":108,"wins":115},"GB2-05":{"draws":0,"losses":343,"wins":301},"GB2-06":{"draws":32,"losses":171,"wins":427},"GB2-07":{"draws":0,"losses":228,"wins":500},"GB2-08":{"draws":161,"losses":195,"wins":394}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":25,"losses":44,"wins":127},"GB2-02":{"draws":85,"losses":3,"wins":134},"GB2-04":{"draws":88,"losses":26,"wins":94},"GB2-05":{"draws":0,"losses":103,"wins":115},"GB2-06":{"draws":10,"losses":21,"wins":155},"GB2-07":{"draws":0,"losses":57,"wins":177},"GB2-08":{"draws":0,"losses":56,"wins":188}},"medium":{"GB2-01":{"draws":50,"losses":77,"wins":91},"GB2-02":{"draws":206,"losses":34,"wins":2},"GB2-03":{"draws":82,"losses":55,"wins":23},"GB2-04":{"draws":180,"losses":42,"wins":10},"GB2-05":{"draws":0,"losses":103,"wins":119},"GB2-06":{"draws":1,"losses":33,"wins":178},"GB2-07":{"draws":0,"losses":70,"wins":190},"GB2-08":{"draws":160,"losses":87,"wins":13}},"none":{"GB2-01":{"draws":42,"losses":60,"wins":86},"GB2-02":{"draws":185,"losses":40,"wins":9},"GB2-04":{"draws":169,"losses":40,"wins":11},"GB2-05":{"draws":0,"losses":137,"wins":67},"GB2-06":{"draws":21,"losses":117,"wins":94},"GB2-07":{"draws":0,"losses":101,"wins":133},"GB2-08":{"draws":1,"losses":52,"wins":193}}},"per_game_raw_elo_all":{"GB2-01":1571.24144600179,"GB2-02":1533.2686277905211,"GB2-04":1465.6402448254003,"GB2-05":1407.9052568577024,"GB2-06":1755.4196585433056,"GB2-07":1699.8349551504937,"GB2-08":1701.7905711012581},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1762.9556975548683,"GB2-02":1747.5557301516608,"GB2-04":1560.4544404266012,"GB2-05":1552.67982618968,"GB2-06":1947.2829917603456,"GB2-07":1817.9100794455105,"GB2-08":1938.4878354589573},"medium":{"GB2-01":1449.627713228418,"GB2-02":1431.9903241236045,"GB2-03":1351.3290956562178,"GB2-04":1435.536382103054,"GB2-05":1459.2935171591985,"GB2-06":1938.123380003363,"GB2-07":1781.3101275704387,"GB2-08":1293.267657118018},"none":{"GB2-01":1501.1409272220847,"GB2-02":1420.2598290962976,"GB2-04":1400.9299119465456,"GB2-05":1211.7424272242288,"GB2-06":1380.8526038662078,"GB2-07":1500.2846584355318,"GB2-08":1873.6162207267992}},"per_game_tracks":{"highest":{"GB2-01":62.246071636380556,"GB2-02":55.13307379115065,"GB2-04":34.85712071940729,"GB2-05":52.44277934918639,"GB2-06":77.2968555369974,"GB2-07":68.20377730883659,"GB2-08":70.55735812782373},"medium":{"GB2-01":39.686527732608575,"GB2-02":11.079767082085603,"GB2-03":23.215693610233096,"GB2-04":15.920680122697588,"GB2-05":46.584634005108285,"GB2-06":76.85512294401404,"GB2-07":65.86852270634525,"GB2-08":20.56556657258231},"none":{"GB2-01":43.26347362679888,"GB2-02":9.375632668651434,"GB2-04":10.504771258695378,"GB2-05":30.942690474762188,"GB2-06":43.28150796494913,"GB2-07":47.17128525880681,"GB2-08":65.5329285510463}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":58.1319266427848,"medium":37.47206434695934,"none":34.55170984764627},"reasoning_agg":{"highest":{"max":77.2968555369974,"mean":58.1319266427848,"min":34.85712071940729},"medium":{"max":76.85512294401404,"mean":37.47206434695934,"min":11.079767082085603},"none":{"max":65.5329285510463,"mean":34.55170984764627,"min":9.375632668651434}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":77.2968555369974,"expected_score":44.63607254622283,"reasoning_variance":23.580216795138526,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.2508389337593542},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.2968555369974,"expected_score":55.52437289242464,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.607553750360161},"medium":{"ceiling_score":76.85512294401404,"expected_score":37.5468419472294,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.07477760027006042},"none":{"ceiling_score":65.5329285510463,"expected_score":37.56610942250825,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.014399574861976}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-2-4t-a95b:9c636bff3b95eabb","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.454226856819533},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8188113672473941},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.2163622471450082,"mean":0.1497312219916341,"median":0.14598267318350014,"min":0.09347384547152984,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1978497759330726}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.17384630544122162,"mean":0.10235142090592425,"median":0.0851321236175097,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.8188113672473941},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.2163622471450082,"mean":0.1497312219916341,"median":0.14598267318350014,"min":0.09347384547152984,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.1978497759330726},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.4317783571024416,"median":0.3306270924500423,"min":0.277380977244658,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.454226856819533}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":27},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.7896974949512139,"mean":0.22795366666666664,"median":0.16679960729572763,"min":0.07156210251142602,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":24,"token_priced_attempt_count":27,"total":5.470887999999999},"codegen_output_tokens":{"attempt_count":27,"output_max":128921,"output_mean":35057.208333333336,"output_min":6291,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":128921,"output_mean":72806.0,"output_min":45821,"run_count":8},"medium":{"attempt_count":8,"output_max":25498,"output_mean":11826.75,"output_min":6291,"run_count":8},"none":{"attempt_count":9,"output_max":34088,"output_mean":20538.875,"output_min":10484,"run_count":8}},"display_name":"Qwen3.8 2.4t A95B","economics":{"all":42.81638537719265,"highest":55.698873819425124,"medium":33.316411998023604,"none":39.43387031412924},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":27,"finish_reasons":["stop"],"indexed_attempts":27,"output_token_observations":27,"provider_post_attempt_observations":27,"provider_post_attempts":27,"reasoning_token_observations":27,"reconciliation_get_attempt_observations":27,"total_output_tokens":841373,"total_reasoning_output_tokens":733891,"total_visible_output_tokens":107482,"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":"qwen","provider_model":"qwen/qwen3.8-2.4t-a95b","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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":"qwen/qwen3.8-2.4t-a95b","is_recent_addition":false,"last_measured_at":"2026-09-26T05:38:14Z","match_totals_all":{"draws":2013,"losses":2159,"wins":2492},"match_totals_tracks":{"highest":{"draws":538,"losses":503,"wins":1059},"medium":{"draws":860,"losses":872,"wins":605},"none":{"draws":615,"losses":784,"wins":828}},"model_slug":"qwen-qwen3-8-2-4t-a95b","overall":{"max":82.70017849652697,"mean":42.81638537719266,"min":12.616204522236107},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":19,"overall_ranking_status":"ranked","per_game":{"GB2-01":45.12613425535377,"GB2-02":22.110849882712547,"GB2-03":70.62630431030064,"GB2-04":18.519703877771764,"GB2-05":66.94402398236382,"GB2-06":80.71921840464294,"GB2-07":58.84457734572849,"GB2-08":82.70017849652697},"per_game_all":{"GB2-01":38.90996043004501,"GB2-02":19.417981125113513,"GB2-03":47.119311893241424,"GB2-04":16.645519883912872,"GB2-05":53.99688259558976,"GB2-06":61.08206577658428,"GB2-07":47.779255148010385,"GB2-08":57.58010616504398},"per_game_match_totals_all":{"GB2-01":{"draws":327,"losses":297,"wins":196},"GB2-02":{"draws":574,"losses":116,"wins":94},"GB2-03":{"draws":295,"losses":267,"wins":266},"GB2-04":{"draws":532,"losses":167,"wins":107},"GB2-05":{"draws":0,"losses":385,"wins":415},"GB2-06":{"draws":77,"losses":308,"wins":485},"GB2-07":{"draws":0,"losses":423,"wins":421},"GB2-08":{"draws":208,"losses":196,"wins":508}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":104,"losses":102,"wins":114},"GB2-02":{"draws":161,"losses":27,"wins":50},"GB2-03":{"draws":103,"losses":41,"wins":96},"GB2-04":{"draws":140,"losses":56,"wins":50},"GB2-05":{"draws":0,"losses":95,"wins":147},"GB2-06":{"draws":28,"losses":44,"wins":186},"GB2-07":{"draws":0,"losses":111,"wins":151},"GB2-08":{"draws":2,"losses":27,"wins":265}},"medium":{"GB2-01":{"draws":111,"losses":89,"wins":48},"GB2-02":{"draws":207,"losses":48,"wins":11},"GB2-03":{"draws":147,"losses":101,"wins":69},"GB2-04":{"draws":168,"losses":52,"wins":20},"GB2-05":{"draws":0,"losses":156,"wins":174},"GB2-06":{"draws":25,"losses":152,"wins":125},"GB2-07":{"draws":0,"losses":160,"wins":126},"GB2-08":{"draws":202,"losses":114,"wins":32}},"none":{"GB2-01":{"draws":112,"losses":106,"wins":34},"GB2-02":{"draws":206,"losses":41,"wins":33},"GB2-03":{"draws":45,"losses":125,"wins":101},"GB2-04":{"draws":224,"losses":59,"wins":37},"GB2-05":{"draws":0,"losses":134,"wins":94},"GB2-06":{"draws":24,"losses":112,"wins":174},"GB2-07":{"draws":0,"losses":152,"wins":144},"GB2-08":{"draws":4,"losses":55,"wins":211}}},"per_game_raw_elo_all":{"GB2-01":1436.1372982428295,"GB2-02":1490.5844944953567,"GB2-03":1598.9022096937545,"GB2-04":1438.5715285818872,"GB2-05":1575.0530322629456,"GB2-06":1672.9775455984247,"GB2-07":1507.2017745885196,"GB2-08":1768.6476889758749},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1520.1200824179782,"GB2-02":1510.9407583918967,"GB2-03":1851.2352620954791,"GB2-04":1451.7269933086907,"GB2-05":1781.8758852254225,"GB2-06":1999.5702904001846,"GB2-07":1675.1426121287288,"GB2-08":2092.7499878056583},"medium":{"GB2-01":1482.2684611119496,"GB2-02":1455.0946017208194,"GB2-03":1468.643838144331,"GB2-04":1413.5545566663732,"GB2-05":1639.231113666521,"GB2-06":1391.7309987241533,"GB2-07":1319.6817188620118,"GB2-08":1340.4179560986631},"none":{"GB2-01":1306.023351198561,"GB2-02":1505.7181233733536,"GB2-03":1476.8275288414534,"GB2-04":1450.4330357705978,"GB2-05":1304.0520978968937,"GB2-06":1627.6313476709363,"GB2-07":1526.780992774818,"GB2-08":1872.7751230233032}},"per_game_tracks":{"highest":{"GB2-01":45.12613425535377,"GB2-02":22.110849882712547,"GB2-03":70.62630431030064,"GB2-04":18.519703877771764,"GB2-05":66.94402398236382,"GB2-06":80.71921840464294,"GB2-07":58.84457734572849,"GB2-08":82.70017849652697},"medium":{"GB2-01":42.169294337090165,"GB2-02":14.48207812927821,"GB2-03":35.0676143238197,"GB2-04":12.616204522236107,"GB2-05":58.20356435343441,"GB2-06":44.1330543606259,"GB2-07":35.37647998531129,"GB2-08":24.48300597239306},"none":{"GB2-01":29.434452697691107,"GB2-02":21.661015363349787,"GB2-03":35.66401704560394,"GB2-04":18.80065125173074,"GB2-05":36.84305945097105,"GB2-06":58.393924564483996,"GB2-07":49.116708112991375,"GB2-08":65.55713402621188}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":55.698873819425124,"medium":33.316411998023604,"none":39.43387031412924},"reasoning_agg":{"highest":{"max":82.70017849652697,"mean":55.698873819425124,"min":18.519703877771764},"medium":{"max":58.20356435343441,"mean":33.316411998023604,"min":12.616204522236107},"none":{"max":65.55713402621188,"mean":39.43387031412924,"min":18.80065125173074}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":82.70017849652697,"expected_score":41.98086600205275,"reasoning_variance":22.38246182140152,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.8355193751399099},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":82.70017849652697,"expected_score":50.363597058820375,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.335276760604749},"medium":{"ceiling_score":58.20356435343441,"expected_score":32.3599771745992,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.9564348234244022},"none":{"ceiling_score":65.55713402621188,"expected_score":43.21902377273866,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.7851534586094218}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-6-flash:bc54536515b1fe37","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.531673125,"mean":0.47737264687500003,"median":0.48302475,"min":0.3855675,"recorded_attempt_count":53,"run_count":16,"total":7.6379623500000005},"medium":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07826175,"mean":0.05584070625,"median":0.0541695,"min":0.0411735,"recorded_attempt_count":29,"run_count":16,"total":0.8934513000000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":44},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":12.70110135},"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":47.09773935857795,"highest":56.543574556619625,"medium":44.801670301819044,"none":31.212059686340446},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T07:10:13Z","match_totals_all":{"draws":4335,"losses":5360,"wins":6658},"match_totals_tracks":{"highest":{"draws":850,"losses":1276,"wins":2507},"medium":{"draws":1172,"losses":1452,"wins":2399},"none":{"draws":2313,"losses":2632,"wins":1752}},"model_slug":"google-gemini-3-6-flash","overall":{"max":84.81723945765842,"mean":42.38751206551634,"min":6.522895012627464},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":20,"overall_ranking_status":"ranked","per_game":{"GB2-01":45.62728002923918,"GB2-03":53.73095376256919,"GB2-04":43.197884951213425,"GB2-05":80.67349142530983,"GB2-06":84.81723945765842,"GB2-07":51.279246637719716,"GB2-08":36.47892563262763},"per_game_all":{"GB2-01":47.6798862663837,"GB2-03":43.553372249347774,"GB2-04":22.197707332723777,"GB2-05":65.78722702215656,"GB2-06":64.23018331726425,"GB2-07":47.288109512623386,"GB2-08":38.947689809546176},"per_game_match_totals_all":{"GB2-01":{"draws":692,"losses":810,"wins":718},"GB2-02":{"draws":837,"losses":123,"wins":9},"GB2-03":{"draws":416,"losses":690,"wins":765},"GB2-04":{"draws":1243,"losses":469,"wins":425},"GB2-05":{"draws":0,"losses":790,"wins":1663},"GB2-06":{"draws":183,"losses":794,"wins":1413},"GB2-07":{"draws":0,"losses":1034,"wins":1123},"GB2-08":{"draws":964,"losses":650,"wins":542}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":233,"losses":260,"wins":265},"GB2-03":{"draws":34,"losses":105,"wins":201},"GB2-04":{"draws":233,"losses":184,"wins":310},"GB2-05":{"draws":0,"losses":115,"wins":599},"GB2-06":{"draws":29,"losses":128,"wins":617},"GB2-07":{"draws":0,"losses":243,"wins":251},"GB2-08":{"draws":321,"losses":241,"wins":264}},"medium":{"GB2-01":{"draws":262,"losses":128,"wins":272},"GB2-02":{"draws":204,"losses":38,"wins":4},"GB2-03":{"draws":146,"losses":307,"wins":245},"GB2-04":{"draws":424,"losses":135,"wins":56},"GB2-05":{"draws":0,"losses":251,"wins":579},"GB2-06":{"draws":69,"losses":111,"wins":618},"GB2-07":{"draws":0,"losses":370,"wins":406},"GB2-08":{"draws":67,"losses":112,"wins":219}},"none":{"GB2-01":{"draws":197,"losses":422,"wins":181},"GB2-02":{"draws":633,"losses":85,"wins":5},"GB2-03":{"draws":236,"losses":278,"wins":319},"GB2-04":{"draws":586,"losses":150,"wins":59},"GB2-05":{"draws":0,"losses":424,"wins":485},"GB2-06":{"draws":85,"losses":555,"wins":178},"GB2-07":{"draws":0,"losses":421,"wins":466},"GB2-08":{"draws":576,"losses":297,"wins":59}}},"per_game_raw_elo_all":{"GB2-01":1554.4411794329724,"GB2-03":1557.5918699458246,"GB2-04":1471.610102745289,"GB2-05":1757.6775035094688,"GB2-06":1721.6367953969293,"GB2-07":1495.2596658317416,"GB2-08":1524.8818658983303},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1525.274977037982,"GB2-03":1666.930551960334,"GB2-04":1608.1157943372193,"GB2-05":1995.6560537713262,"GB2-06":2062.902643613834,"GB2-07":1554.2072105491354,"GB2-08":1493.300436992121},"medium":{"GB2-01":1794.1274585311537,"GB2-02":1407.0006676265327,"GB2-03":1487.2431326874294,"GB2-04":1371.099783353723,"GB2-05":1757.0745917859986,"GB2-06":1950.1732139346586,"GB2-07":1409.6014825484217,"GB2-08":1760.9174300104548},"none":{"GB2-01":1343.9211027297813,"GB2-02":1400.0460729275737,"GB2-03":1518.6019251897103,"GB2-04":1435.6147305449247,"GB2-05":1520.301864971082,"GB2-06":1151.834528642296,"GB2-07":1521.9703043976683,"GB2-08":1320.427730692415}},"per_game_tracks":{"highest":{"GB2-01":45.62728002923918,"GB2-03":53.73095376256919,"GB2-04":43.197884951213425,"GB2-05":80.67349142530983,"GB2-06":84.81723945765842,"GB2-07":51.279246637719716,"GB2-08":36.47892563262763},"medium":{"GB2-01":64.86230382138523,"GB2-02":7.60791714849584,"GB2-03":36.90988791045416,"GB2-04":6.522895012627464,"GB2-05":65.76089456908176,"GB2-06":78.02975880638576,"GB2-07":41.50853013969376,"GB2-08":57.21117500642834},"none":{"GB2-01":32.55007494852668,"GB2-02":7.254418122980565,"GB2-03":40.019275075019976,"GB2-04":16.872342034330437,"GB2-05":50.927295072078095,"GB2-06":29.843551687748583,"GB2-07":49.07655176045668,"GB2-08":23.152968789582562}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.61972523339207,"medium":43.3307512768165,"none":31.212059686340446},"reasoning_agg":{"highest":{"max":84.81723945765842,"mean":52.61972523339207,"min":36.47892563262763},"medium":{"max":78.02975880638576,"mean":43.3307512768165,"min":6.522895012627464},"none":{"max":50.927295072078095,"mean":31.212059686340446,"min":7.254418122980565}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":84.81723945765842,"expected_score":45.6219845686608,"reasoning_variance":21.40766554705162,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.2344725031444597},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":84.81723945765842,"expected_score":49.8195724720866,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.800152761305469},"medium":{"ceiling_score":78.02975880638576,"expected_score":45.94430346539269,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.613552188576193},"none":{"ceiling_score":50.927295072078095,"expected_score":31.528648639591516,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.3165889532510704}}},{"canonical_public_row_identity":"publication-row.v1:overall:stealth-ox-alpha:73d3ab9aca3d929b","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":25,"cell_count":8,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":42.69405202545458,"highest":56.96197216987767,"medium":37.44522449771469,"none":33.67495940877139},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":{"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":{"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":{"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":"2026-09-26T05:45:11Z","match_totals_all":{"draws":5484,"losses":7660,"wins":8541},"match_totals_tracks":{"highest":{"draws":900,"losses":1995,"wins":3666},"medium":{"draws":1742,"losses":2765,"wins":2711},"none":{"draws":2842,"losses":2900,"wins":2164}},"model_slug":"stealth-ox-alpha","overall":{"max":66.94082807294467,"mean":42.06345731349799,"min":13.294890921207008},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":21,"overall_ranking_status":"ranked","per_game":{"GB2-01":48.797529806037005,"GB2-02":51.29469725684797,"GB2-03":57.324992530773876,"GB2-04":55.582826781283906,"GB2-05":59.15504083513043,"GB2-06":66.94082807294467,"GB2-07":59.457789483674446,"GB2-08":57.142072592329065},"per_game_all":{"GB2-01":47.78956395299357,"GB2-02":26.325852885393292,"GB2-03":43.984251068448486,"GB2-04":36.86920695825637,"GB2-05":53.34383209706161,"GB2-06":46.87335108290407,"GB2-07":46.33578281247764,"GB2-08":40.030575346101635},"per_game_match_totals_all":{"GB2-01":{"draws":402,"losses":888,"wins":1042},"GB2-02":{"draws":1347,"losses":263,"wins":380},"GB2-03":{"draws":1554,"losses":1562,"wins":1870},"GB2-04":{"draws":1189,"losses":471,"wins":743},"GB2-05":{"draws":0,"losses":1163,"wins":1287},"GB2-06":{"draws":152,"losses":1242,"wins":1072},"GB2-07":{"draws":0,"losses":1401,"wins":1349},"GB2-08":{"draws":840,"losses":670,"wins":798}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":51,"losses":366,"wins":393},"GB2-02":{"draws":176,"losses":43,"wins":279},"GB2-03":{"draws":211,"losses":254,"wins":614},"GB2-04":{"draws":239,"losses":96,"wins":391},"GB2-05":{"draws":0,"losses":349,"wins":457},"GB2-06":{"draws":96,"losses":279,"wins":511},"GB2-07":{"draws":0,"losses":351,"wins":557},"GB2-08":{"draws":127,"losses":257,"wins":464}},"medium":{"GB2-01":{"draws":122,"losses":179,"wins":333},"GB2-02":{"draws":559,"losses":101,"wins":76},"GB2-03":{"draws":336,"losses":684,"wins":826},"GB2-04":{"draws":404,"losses":168,"wins":202},"GB2-05":{"draws":0,"losses":420,"wins":382},"GB2-06":{"draws":30,"losses":427,"wins":171},"GB2-07":{"draws":0,"losses":476,"wins":396},"GB2-08":{"draws":291,"losses":310,"wins":325}},"none":{"GB2-01":{"draws":229,"losses":343,"wins":316},"GB2-02":{"draws":612,"losses":119,"wins":25},"GB2-03":{"draws":1007,"losses":624,"wins":430},"GB2-04":{"draws":546,"losses":207,"wins":150},"GB2-05":{"draws":0,"losses":394,"wins":448},"GB2-06":{"draws":26,"losses":536,"wins":390},"GB2-07":{"draws":0,"losses":574,"wins":396},"GB2-08":{"draws":422,"losses":103,"wins":9}}},"per_game_raw_elo_all":{"GB2-01":1558.059088786188,"GB2-02":1540.5192957488177,"GB2-03":1567.0716092272312,"GB2-04":1570.4947722139786,"GB2-05":1564.3164267860495,"GB2-06":1437.0452938978235,"GB2-07":1484.5930505995595,"GB2-08":1543.110549308537},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1572.980147629157,"GB2-02":1718.6964800993865,"GB2-03":1711.1704825779957,"GB2-04":1693.5681896146361,"GB2-05":1656.8369568686655,"GB2-06":1769.8930114176446,"GB2-07":1682.7877978368622,"GB2-08":1763.8054792817131},"medium":{"GB2-01":1650.141425370019,"GB2-02":1455.5296895697975,"GB2-03":1550.4692820095286,"GB2-04":1516.3337544286576,"GB2-05":1473.1421956365666,"GB2-06":1152.952993622689,"GB2-07":1426.5799659583142,"GB2-08":1539.6759692111352},"none":{"GB2-01":1451.0556933593878,"GB2-02":1447.3317175772688,"GB2-03":1439.5750630941693,"GB2-04":1501.5823725986418,"GB2-05":1562.9701278529164,"GB2-06":1388.2898766531368,"GB2-07":1344.4113880035022,"GB2-08":1325.8501994327623}},"per_game_tracks":{"highest":{"GB2-01":48.797529806037005,"GB2-02":51.29469725684797,"GB2-03":57.324992530773876,"GB2-04":55.582826781283906,"GB2-05":59.15504083513043,"GB2-06":66.94082807294467,"GB2-07":59.457789483674446,"GB2-08":57.142072592329065},"medium":{"GB2-01":54.520370352591726,"GB2-02":14.387970478124894,"GB2-03":42.524967831534816,"GB2-04":28.514946002355497,"GB2-05":47.59564713052516,"GB2-06":29.73103194706969,"GB2-07":42.455397132660124,"GB2-08":39.831465106855575},"none":{"GB2-01":40.05079170035196,"GB2-02":13.294890921207008,"GB2-03":32.10279284303678,"GB2-04":26.509848091129715,"GB2-05":53.28080832552923,"GB2-06":43.948193228697846,"GB2-07":37.094161821098346,"GB2-08":23.11818833912026}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":56.96197216987767,"medium":36.12929290714516,"none":33.09910686347114},"reasoning_agg":{"highest":{"max":66.94082807294467,"mean":56.96197216987767,"min":48.797529806037005},"medium":{"max":54.520370352591726,"mean":36.12929290714516,"min":14.387970478124894},"none":{"max":53.28080832552923,"mean":33.09910686347114,"min":13.294890921207008}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":66.94082807294467,"expected_score":41.115701508002985,"reasoning_variance":23.862865306406526,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.9477558054950066},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":66.94082807294467,"expected_score":50.92714065041585,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.034831519461818},"medium":{"ceiling_score":54.520370352591726,"expected_score":36.63560956545905,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.5063166583138923},"none":{"ceiling_score":53.28080832552923,"expected_score":35.78435430813406,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.68524744466292}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-3-flashx:4100dadd8ed38338","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.060370179999999996,"median":0.057823150000000004,"min":0.03447845,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.48296143999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558000000003},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01270098,"mean":0.0085203375,"median":0.007669445,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.0681627}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.039202100000000004,"mean":0.026445697500000004,"median":0.025158225,"min":0.015228470000000001,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.21156558},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01270098,"mean":0.0085203375,"median":0.007669445,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.0681627},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.060370179999999996,"median":0.057823150000000004,"min":0.03447845,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.48296143999999996}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.09557687,"mean":0.03177873833333334,"median":0.025158225,"min":0.00543595,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":29},"recorded_attempt_count":29,"run_count":24,"total":0.7626897200000001},"codegen_latency_ms":{"attempt_count":29,"max_ms":579647,"mean_ms":182597.75,"min_ms":15305,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":579647,"mean_ms":375199.125,"min_ms":217884,"run_count":8},"medium":{"attempt_count":11,"max_ms":196176,"mean_ms":145630.0,"min_ms":61522,"run_count":8},"none":{"attempt_count":10,"max_ms":51111,"mean_ms":26964.125,"min_ms":15305,"run_count":8}},"codegen_output_tokens":{"attempt_count":29,"output_max":74293,"output_mean":22693.125,"output_min":2253,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":74293,"output_mean":46016.5,"output_min":25493,"run_count":8},"medium":{"attempt_count":11,"output_max":25418,"output_mean":18052.125,"output_min":8262,"run_count":8},"none":{"attempt_count":10,"output_max":6651,"output_mean":4010.75,"output_min":2253,"run_count":8}},"display_name":"GLM-5.3 FlashX","economics":{"all":41.720019947405675,"highest":50.902147617314895,"medium":37.13889244533413,"none":37.119019779568006},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":29,"effective_max_output_tokens":[131072],"finish_reason_observations":29,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"provider_post_attempt_observations":29,"provider_post_attempts":29,"reasoning_token_observations":29,"reconciliation_get_attempt_observations":29,"requested_max_output_token_observations":29,"requested_max_output_tokens":[131072],"total_output_tokens":544635,"total_reasoning_output_tokens":454317,"total_visible_output_tokens":90318,"visible_token_observations":29},"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":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"z-ai","provider_model":"z-ai/glm-5.3-flashx","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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,"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":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":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"z-ai/glm-5.3-flashx","is_recent_addition":false,"last_measured_at":"2026-09-26T06:08:30Z","match_totals_all":{"draws":556,"losses":788,"wins":917},"match_totals_tracks":{"highest":{"draws":158,"losses":210,"wins":401},"medium":{"draws":183,"losses":277,"wins":268},"none":{"draws":215,"losses":301,"wins":248}},"model_slug":"z-ai-glm-5-3-flashx","overall":{"max":69.68349991872405,"mean":41.720019947405675,"min":6.304310183382496},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":22,"overall_ranking_status":"ranked","per_game":{"GB2-01":34.87203056930424,"GB2-02":37.10396280934647,"GB2-03":57.76110043464071,"GB2-04":59.353406503954446,"GB2-05":57.68901207039583,"GB2-06":68.56175149952885,"GB2-07":69.68349991872405,"GB2-08":22.192417132624534},"per_game_all":{"GB2-01":48.49214247114984,"GB2-02":21.89970795581841,"GB2-03":42.31834992283034,"GB2-04":37.77089970801374,"GB2-05":48.50492866513429,"GB2-06":59.4397017104699,"GB2-07":59.16930175615985,"GB2-08":16.165127389669042},"per_game_match_totals_all":{"GB2-01":{"draws":21,"losses":91,"wins":148},"GB2-02":{"draws":214,"losses":45,"wins":59},"GB2-03":{"draws":27,"losses":81,"wins":94},"GB2-04":{"draws":144,"losses":39,"wins":88},"GB2-05":{"draws":0,"losses":153,"wins":127},"GB2-06":{"draws":13,"losses":114,"wins":177},"GB2-07":{"draws":0,"losses":104,"wins":202},"GB2-08":{"draws":137,"losses":161,"wins":22}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":55,"wins":35},"GB2-02":{"draws":55,"losses":11,"wins":42},"GB2-03":{"draws":1,"losses":15,"wins":52},"GB2-04":{"draws":33,"losses":6,"wins":52},"GB2-05":{"draws":0,"losses":33,"wins":53},"GB2-06":{"draws":6,"losses":23,"wins":81},"GB2-07":{"draws":0,"losses":25,"wins":73},"GB2-08":{"draws":63,"losses":42,"wins":13}},"medium":{"GB2-01":{"draws":3,"losses":15,"wins":68},"GB2-02":{"draws":78,"losses":8,"wins":16},"GB2-03":{"draws":10,"losses":31,"wins":27},"GB2-04":{"draws":54,"losses":16,"wins":22},"GB2-05":{"draws":0,"losses":66,"wins":28},"GB2-06":{"draws":3,"losses":42,"wins":45},"GB2-07":{"draws":0,"losses":40,"wins":60},"GB2-08":{"draws":35,"losses":59,"wins":2}},"none":{"GB2-01":{"draws":18,"losses":21,"wins":45},"GB2-02":{"draws":81,"losses":26,"wins":1},"GB2-03":{"draws":16,"losses":35,"wins":15},"GB2-04":{"draws":57,"losses":17,"wins":14},"GB2-05":{"draws":0,"losses":54,"wins":46},"GB2-06":{"draws":4,"losses":49,"wins":51},"GB2-07":{"draws":0,"losses":39,"wins":69},"GB2-08":{"draws":39,"losses":60,"wins":7}}},"per_game_raw_elo_all":{"GB2-01":1587.0592848180213,"GB2-02":1522.2395988311255,"GB2-03":1571.9388122248913,"GB2-04":1593.6422597099217,"GB2-05":1504.2813662811252,"GB2-06":1661.9148435266331,"GB2-07":1694.8201151083056,"GB2-08":1250.4343657825295},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1397.9749578962649,"GB2-02":1630.396353719646,"GB2-03":1736.4077562989137,"GB2-04":1734.1899857520896,"GB2-05":1651.9483960765153,"GB2-06":1811.3219268551459,"GB2-07":1854.3647282372995,"GB2-08":1326.1473083609105},"medium":{"GB2-01":1810.7430830542555,"GB2-02":1501.9966307130856,"GB2-03":1562.4825057520145,"GB2-04":1530.2645516104485,"GB2-05":1314.2075764563135,"GB2-06":1503.4273717215772,"GB2-07":1576.731004871293,"GB2-08":1125.2858864123048},"none":{"GB2-01":1552.4598135035433,"GB2-02":1434.3258120606447,"GB2-03":1416.9261746237462,"GB2-04":1516.4722417672274,"GB2-05":1546.6881263105474,"GB2-06":1670.995232003176,"GB2-07":1653.3646122163236,"GB2-08":1299.869902574373}},"per_game_tracks":{"highest":{"GB2-01":34.87203056930424,"GB2-02":37.10396280934647,"GB2-03":57.76110043464071,"GB2-04":59.353406503954446,"GB2-05":57.68901207039583,"GB2-06":68.56175149952885,"GB2-07":69.68349991872405,"GB2-08":22.192417132624534},"medium":{"GB2-01":64.66231754539399,"GB2-02":18.96089415153658,"GB2-03":41.45403256955391,"GB2-04":28.108135352354548,"GB2-05":36.56312275285062,"GB2-06":49.73266361940691,"GB2-07":51.325663388194,"GB2-08":6.304310183382496},"none":{"GB2-01":45.94207929875129,"GB2-02":9.634266906572186,"GB2-03":27.7399167642964,"GB2-04":25.851157267732205,"GB2-05":51.262651172156424,"GB2-06":60.02469001247392,"GB2-07":56.498741961561485,"GB2-08":19.998654853000097}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.902147617314895,"medium":37.13889244533413,"none":37.119019779568006},"reasoning_agg":{"highest":{"max":69.68349991872405,"mean":50.902147617314895,"min":22.192417132624534},"medium":{"max":64.66231754539399,"mean":37.13889244533413,"min":6.304310183382496},"none":{"max":60.02469001247392,"mean":37.119019779568006,"min":9.634266906572186}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":69.68349991872405,"expected_score":41.85160029743998,"reasoning_variance":13.783127837746889,"reliability_score":92.08725399163767,"uncertainty_avg":7.912746008362334,"uncertainty_penalty":0.13158035003430513},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":69.68349991872405,"expected_score":45.464373127305905,"reliability_score":92.52782146272592,"uncertainty_avg":7.472178537274081,"uncertainty_penalty":-5.437774490008991},"medium":{"ceiling_score":64.66231754539399,"expected_score":38.57802571692992,"reliability_score":91.35688385786946,"uncertainty_avg":8.643116142130538,"uncertainty_penalty":1.439133271595793},"none":{"ceiling_score":60.02469001247392,"expected_score":41.51240204808411,"reliability_score":92.37705665431761,"uncertainty_avg":7.622943345682389,"uncertainty_penalty":4.393382268516106}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash:2fe322b9f9e7e988","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.5094276945411561,"mean":0.27056867355814085,"median":0.2333324037943521,"min":0.1875185140307643,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.164549388465127},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478314},"none":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.12650943660072694,"mean":0.07695988119919009,"median":0.07334251535992004,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"recorded_attempt_count":14,"run_count":16,"token_priced_attempt_count":11,"total":1.2313580991870416}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.27117240812024124,"mean":0.1983136265434789,"median":0.18868274576048882,"min":0.15676593388665558,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":1.5865090123478314},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"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-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.13084687320145388,"mean":0.0871504498983802,"median":0.08084431374719805,"min":0.0619993303028941,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":0.6972035991870416},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":11},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.5094276945411561,"mean":0.27056867355814085,"median":0.2333324037943521,"min":0.1875185140307643,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":11},"run_count":8,"token_priced_attempt_count":11,"total":2.1645493884651272}},"codegen_cost_usd":{"admitted_cell_count":30,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":32,"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Combined: Provider-reported + Standard list-price estimate","failed_cell_count":2,"max":0.5094276945411561,"mean":0.1819473937669366,"median":0.18692147314407714,"min":0.043710665151447045,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":32},"recorded_attempt_count":14,"run_count":32,"token_priced_attempt_count":32,"total":4.982416500000001},"codegen_output_tokens":{"attempt_count":32,"output_max":60921,"output_mean":18651.916666666668,"output_min":1790,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":60921,"output_mean":31693.5,"output_min":21144,"run_count":8},"medium":{"attempt_count":10,"output_max":28586,"output_mean":21214.875,"output_min":16507,"run_count":8},"none":{"attempt_count":11,"output_max":4623,"output_mean":3047.375,"output_min":1790,"run_count":8}},"display_name":"Gemini 3.5 Flash","economics":{"all":40.53941893541795,"highest":50.89735281045077,"medium":46.185201092299764,"none":24.535702903503303},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["stop"],"indexed_attempts":32,"output_token_observations":32,"provider_post_attempt_observations":32,"provider_post_attempts":32,"reasoning_token_observations":32,"reconciliation_get_attempt_observations":32,"total_output_tokens":447646,"total_reasoning_output_tokens":288780,"total_visible_output_tokens":158866,"visible_token_observations":32},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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},"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":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":0.375},"intensive":{"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":"google/gemini-3.5-flash","is_recent_addition":false,"last_measured_at":"2026-09-26T04:32:10Z","match_totals_all":{"draws":2000,"losses":2711,"wins":2644},"match_totals_tracks":{"highest":{"draws":478,"losses":722,"wins":1060},"medium":{"draws":574,"losses":700,"wins":855},"none":{"draws":948,"losses":1289,"wins":729}},"model_slug":"google-gemini-3-5-flash","overall":{"max":83.06075836479648,"mean":40.53941893541795,"min":3.2053701417799094},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["fixed_coverage_incomplete"],"overall_official_rank":23,"overall_ranking_status":"partial","per_game":{"GB2-01":83.06075836479648,"GB2-02":26.975014405775077,"GB2-03":55.588815089736755,"GB2-04":14.461692225008958,"GB2-05":59.926695619111804,"GB2-06":70.46431811230623,"GB2-07":53.7877131687657,"GB2-08":42.91381549810512},"per_game_all":{"GB2-01":64.31936246957618,"GB2-02":14.279571120711267,"GB2-03":39.520084547962654,"GB2-04":20.826223129222964,"GB2-05":49.03869413404187,"GB2-06":61.61496667698165,"GB2-07":48.751258567275364,"GB2-08":25.965190837571622},"per_game_match_totals_all":{"GB2-01":{"draws":97,"losses":224,"wins":497},"GB2-02":{"draws":592,"losses":126,"wins":86},"GB2-03":{"draws":177,"losses":283,"wins":251},"GB2-04":{"draws":553,"losses":214,"wins":159},"GB2-05":{"draws":0,"losses":538,"wins":398},"GB2-06":{"draws":32,"losses":413,"wins":515},"GB2-07":{"draws":0,"losses":582,"wins":606},"GB2-08":{"draws":549,"losses":331,"wins":132}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":12,"losses":24,"wins":186},"GB2-02":{"draws":147,"losses":39,"wins":82},"GB2-03":{"draws":67,"losses":72,"wins":103},"GB2-04":{"draws":140,"losses":92,"wins":50},"GB2-05":{"draws":0,"losses":145,"wins":173},"GB2-06":{"draws":9,"losses":75,"wins":162},"GB2-07":{"draws":0,"losses":187,"wins":189},"GB2-08":{"draws":103,"losses":88,"wins":115}},"medium":{"GB2-01":{"draws":5,"losses":77,"wins":152},"GB2-02":{"draws":230,"losses":44,"wins":2},"GB2-03":{"draws":57,"losses":65,"wins":107},"GB2-04":{"draws":134,"losses":59,"wins":67},"GB2-05":{"draws":0,"losses":98,"wins":156},"GB2-06":{"draws":13,"losses":75,"wins":160},"GB2-07":{"draws":0,"losses":156,"wins":210},"GB2-08":{"draws":135,"losses":126,"wins":1}},"none":{"GB2-01":{"draws":80,"losses":123,"wins":159},"GB2-02":{"draws":215,"losses":43,"wins":2},"GB2-03":{"draws":53,"losses":146,"wins":41},"GB2-04":{"draws":279,"losses":63,"wins":42},"GB2-05":{"draws":0,"losses":295,"wins":69},"GB2-06":{"draws":10,"losses":263,"wins":193},"GB2-07":{"draws":0,"losses":239,"wins":207},"GB2-08":{"draws":311,"losses":117,"wins":16}}},"per_game_raw_elo_all":{"GB2-01":1791.0495151797948,"GB2-02":1453.5633908316597,"GB2-03":1519.635210805968,"GB2-04":1467.2177457258656,"GB2-05":1497.6944856273194,"GB2-06":1684.215519477798,"GB2-07":1520.95308190184,"GB2-08":1362.9947241969921},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2048.980958794349,"GB2-02":1544.1743033537418,"GB2-03":1690.744622189022,"GB2-04":1423.5973077877602,"GB2-05":1667.0381081213309,"GB2-06":1830.318546130655,"GB2-07":1594.711589672627,"GB2-08":1579.4199588832294},"medium":{"GB2-01":1809.742799107173,"GB2-02":1441.6312883192647,"GB2-03":1609.8328927398125,"GB2-04":1567.2960941462807,"GB2-05":1803.8778228195865,"GB2-06":1846.6043607048002,"GB2-07":1590.3608593281567,"GB2-08":1201.1802064230644},"none":{"GB2-01":1514.424787637862,"GB2-02":1374.8845808219733,"GB2-03":1258.3281174890685,"GB2-04":1410.7598352435557,"GB2-05":1022.167525941041,"GB2-06":1375.7236515979382,"GB2-07":1377.7867967047368,"GB2-08":1308.3840072846826}},"per_game_tracks":{"highest":{"GB2-01":83.06075836479648,"GB2-02":26.975014405775077,"GB2-03":55.588815089736755,"GB2-04":14.461692225008958,"GB2-05":59.926695619111804,"GB2-06":70.46431811230623,"GB2-07":53.7877131687657,"GB2-08":42.91381549810512},"medium":{"GB2-01":65.80462954922906,"GB2-02":12.658328814578814,"GB2-03":47.93555032425992,"GB2-04":36.35278663265906,"GB2-05":68.36625005086651,"GB2-06":71.45378737958275,"GB2-07":53.481156533970726,"GB2-08":13.429119453251325},"none":{"GB2-01":44.092699494702984,"GB2-02":3.2053701417799094,"GB2-03":15.035888229891286,"GB2-04":11.664190530000868,"GB2-05":18.823136732147315,"GB2-06":42.92679453905597,"GB2-07":38.98490599908969,"GB2-08":21.55263756135841}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.89735281045077,"medium":46.185201092299764,"none":24.535702903503303},"reasoning_agg":{"highest":{"max":83.06075836479648,"mean":50.89735281045077,"min":14.461692225008958},"medium":{"max":71.45378737958275,"mean":46.185201092299764,"min":12.658328814578814},"none":{"max":44.092699494702984,"mean":24.535702903503303,"min":3.2053701417799094}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":83.06075836479648,"expected_score":39.0256334260688,"reasoning_variance":26.361649906947466,"reliability_score":99.92878319615038,"uncertainty_avg":0.07121680384962878,"uncertainty_penalty":-1.5137855093491481},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":83.06075836479648,"expected_score":44.40889663136479,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.488456179085979},"medium":{"ceiling_score":71.45378737958275,"expected_score":47.702251674490604,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.5170505821908407},"none":{"ceiling_score":44.092699494702984,"expected_score":24.965751972351004,"reliability_score":99.78634958845112,"uncertainty_avg":0.2136504115488863,"uncertainty_penalty":0.4300490688477012}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-6-flash:492403cf5d25ef55","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02304638,"mean":0.0178225775,"median":0.01816367,"min":0.01029504,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.14258062000000002},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00414456,"mean":0.0029296749999999996,"median":0.00284053,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"recorded_attempt_count":12,"run_count":8,"total":0.023437400000000004}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.02304638,"mean":0.0178225775,"median":0.01816367,"min":0.01029504,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":11},"recorded_attempt_count":11,"run_count":8,"total":0.14258062},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00414456,"mean":0.0029296749999999996,"median":0.00284053,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"recorded_attempt_count":12,"run_count":8,"total":0.023437400000000004}},"codegen_cost_usd":{"admitted_cell_count":15,"cell_count":16,"cost_basis_counts":{"provider_reported":23},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02304638,"mean":0.01037612625,"median":0.0072198,"min":0.00188342,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":23},"recorded_attempt_count":23,"run_count":16,"total":0.16601802},"codegen_latency_ms":{"attempt_count":23,"max_ms":1374551,"mean_ms":491530.125,"min_ms":35032,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":1374551,"mean_ms":925316.625,"min_ms":428464,"run_count":8},"none":{"attempt_count":12,"max_ms":114099,"mean_ms":57743.625,"min_ms":35032,"run_count":8}},"codegen_output_tokens":{"attempt_count":23,"output_max":78655,"output_mean":31302.375,"output_min":3072,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":78655,"output_mean":57997.125,"output_min":33074,"run_count":8},"none":{"attempt_count":12,"output_max":6869,"output_mean":4607.625,"output_min":3072,"run_count":8}},"display_name":"MiMo-V2.6-Flash","economics":{"medium":46.47158195587396,"none":35.77998902000319},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":23,"effective_max_output_tokens":[131072],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":23,"output_token_observations":23,"provider_post_attempt_observations":23,"provider_post_attempts":23,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":23,"requested_max_output_token_observations":23,"requested_max_output_tokens":[131072],"total_output_tokens":500838,"total_reasoning_output_tokens":411817,"total_visible_output_tokens":89021,"visible_token_observations":23},"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":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"xiaomi","provider_model":"xiaomi/mimo-v2.6-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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,"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":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}},"id":"xiaomi/mimo-v2.6-flash","is_recent_addition":false,"last_measured_at":"2026-09-26T05:39:15Z","match_totals_all":{"draws":321,"losses":528,"wins":551},"match_totals_tracks":{"medium":{"draws":136,"losses":227,"wins":369},"none":{"draws":185,"losses":301,"wins":182}},"model_slug":"xiaomi-mimo-v2-6-flash","overall":{"max":74.75594339279257,"mean":40.538424947479356,"min":10.64791576855527},"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":24,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":17,"losses":58,"wins":89},"GB2-02":{"draws":130,"losses":36,"wins":44},"GB2-03":{"draws":19,"losses":63,"wins":52},"GB2-04":{"draws":14,"losses":23,"wins":47},"GB2-05":{"draws":0,"losses":89,"wins":97},"GB2-06":{"draws":16,"losses":80,"wins":106},"GB2-07":{"draws":0,"losses":80,"wins":114},"GB2-08":{"draws":125,"losses":99,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":2,"losses":38,"wins":44},"GB2-02":{"draws":41,"losses":12,"wins":43},"GB2-03":{"draws":5,"losses":26,"wins":37},"GB2-04":{"draws":14,"losses":23,"wins":47},"GB2-05":{"draws":0,"losses":40,"wins":54},"GB2-06":{"draws":9,"losses":34,"wins":61},"GB2-07":{"draws":0,"losses":11,"wins":81},"GB2-08":{"draws":65,"losses":43,"wins":2}},"none":{"GB2-01":{"draws":15,"losses":20,"wins":45},"GB2-02":{"draws":89,"losses":24,"wins":1},"GB2-03":{"draws":14,"losses":37,"wins":15},"GB2-05":{"draws":0,"losses":49,"wins":43},"GB2-06":{"draws":7,"losses":46,"wins":45},"GB2-07":{"draws":0,"losses":69,"wins":33},"GB2-08":{"draws":60,"losses":56,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1491.37040347236,"GB2-02":1617.010879722701,"GB2-03":1505.698710730232,"GB2-04":1671.1946908389016,"GB2-05":1633.7382771265356,"GB2-06":1672.9595522248487,"GB2-07":1932.243570495013,"GB2-08":1276.26335319047},"none":{"GB2-01":1684.0385013646637,"GB2-02":1440.548077903234,"GB2-03":1411.699634188067,"GB2-05":1547.972010691422,"GB2-06":1569.7518252888142,"GB2-07":1348.283642622752,"GB2-08":1245.0207813422464}},"per_game_tracks":{"medium":{"GB2-01":41.52293240057557,"GB2-02":34.90629945335721,"GB2-03":36.13003736962925,"GB2-04":49.43248729691246,"GB2-05":56.65976344712501,"GB2-06":60.14328939073963,"GB2-07":74.75594339279257,"GB2-08":18.22190289585994},"none":{"GB2-01":55.383789951761365,"GB2-02":10.64791576855527,"GB2-03":27.24988125009566,"GB2-05":51.23795286812163,"GB2-06":53.84156687363663,"GB2-07":36.224069656264476,"GB2-08":15.874746771587313}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":46.47158195587396,"none":34.60526793908475},"reasoning_agg":{"medium":{"max":74.75594339279257,"mean":46.47158195587396,"min":18.22190289585994},"none":{"max":55.383789951761365,"mean":34.60526793908475,"min":10.64791576855527}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":74.75594339279257,"reasoning_variance":11.866314016789211},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":74.75594339279257,"expected_score":49.47017381607031,"reliability_score":91.39689131440947,"uncertainty_avg":8.603108685590527,"uncertainty_penalty":2.998591860196349},"none":{"ceiling_score":55.383789951761365,"expected_score":39.859242466016426,"reliability_score":92.19907515635389,"uncertainty_avg":7.800924843646114,"uncertainty_penalty":5.253974526931678}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max-0902:077c2f0da5fabd7f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.606316,"mean":0.33312575,"median":0.357252,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":9,"run_count":8,"total":2.665006},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.278232,"mean":0.1058585,"median":0.088878,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.846868},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.212408,"mean":0.12122175,"median":0.11379500000000001,"min":0.08249,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.9697739999999999}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.278232,"mean":0.1058585,"median":0.088878,"min":0.054514,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.846868},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.212408,"mean":0.12122175,"median":0.11379500000000001,"min":0.08249,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":10},"recorded_attempt_count":10,"run_count":8,"total":0.9697739999999999},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.606316,"mean":0.33312575,"median":0.357252,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":9,"run_count":8,"total":2.665006}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.606316,"mean":0.18673533333333334,"median":0.11641699999999999,"min":0.0,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":28},"recorded_attempt_count":29,"run_count":24,"total":4.481648000000001},"codegen_latency_ms":{"attempt_count":28,"max_ms":2404956,"mean_ms":688441.3478260869,"min_ms":135091,"run_count":23},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":2404956,"mean_ms":1516855.142857143,"min_ms":951741,"run_count":7},"medium":{"attempt_count":10,"max_ms":878124,"mean_ms":297986.875,"min_ms":135091,"run_count":8},"none":{"attempt_count":10,"max_ms":640944,"mean_ms":354033.75,"min_ms":208254,"run_count":8}},"codegen_output_tokens":{"attempt_count":29,"output_max":94258,"output_mean":28537.75,"output_min":6298,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":94258,"output_mean":54376.5,"output_min":13896,"run_count":8},"medium":{"attempt_count":10,"output_max":40870,"output_mean":14338.625,"output_min":6298,"run_count":8},"none":{"attempt_count":10,"output_max":30162,"output_mean":16898.125,"output_min":10952,"run_count":8}},"display_name":"Qwen3.8 Max 0902","economics":{"all":39.78725879075181,"highest":54.80519325258838,"medium":33.56348020514619,"none":33.10169639730334},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":29,"effective_max_output_tokens":[131072],"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":29,"output_token_observations":29,"provider_post_attempt_observations":29,"provider_post_attempts":30,"reasoning_token_observations":29,"reconciliation_get_attempt_observations":29,"requested_max_output_token_observations":29,"requested_max_output_tokens":[131072],"total_output_tokens":684906,"total_reasoning_output_tokens":570415,"total_visible_output_tokens":114491,"visible_token_observations":29},"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":131072,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"qwen","provider_model":"qwen/qwen3.8-max-0902","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":6,"first_pass_rate":0.75,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":7,"evaluated_cells":7,"first_pass_admitted":6,"first_pass_rate":0.8571428571428571,"infra_excluded_game_aliases":["GB2-07"],"infra_failures_excluded":1,"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},"repaired_admitted":1,"repaired_rate":0.14285714285714285}},"id":"qwen/qwen3.8-max-0902","is_recent_addition":false,"last_measured_at":"2026-09-26T05:43:53Z","match_totals_all":{"draws":597,"losses":631,"wins":829},"match_totals_tracks":{"highest":{"draws":154,"losses":79,"wins":379},"medium":{"draws":205,"losses":297,"wins":231},"none":{"draws":238,"losses":255,"wins":219}},"model_slug":"qwen-qwen3-8-max-0902","overall":{"max":77.95231468763828,"mean":40.490123285012636,"min":0.4051207679024251},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":25,"overall_ranking_status":"partial","per_game":{"GB2-01":50.71505113886677,"GB2-02":32.788493526983785,"GB2-03":51.6714073670336,"GB2-04":61.4397821649466,"GB2-05":77.95231468763828,"GB2-06":71.90040976427079,"GB2-08":37.16889411837889},"per_game_all":{"GB2-01":36.29424381441058,"GB2-02":19.64205329839538,"GB2-03":42.76643753991067,"GB2-04":26.448101579110414,"GB2-05":58.63597557422796,"GB2-06":65.8053125060544,"GB2-08":28.91868722315321},"per_game_match_totals_all":{"GB2-01":{"draws":66,"losses":96,"wins":64},"GB2-02":{"draws":212,"losses":44,"wins":46},"GB2-03":{"draws":24,"losses":63,"wins":117},"GB2-04":{"draws":118,"losses":64,"wins":79},"GB2-05":{"draws":0,"losses":90,"wins":166},"GB2-06":{"draws":20,"losses":68,"wins":208},"GB2-07":{"draws":0,"losses":113,"wins":83},"GB2-08":{"draws":157,"losses":93,"wins":66}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":25,"losses":14,"wins":35},"GB2-02":{"draws":62,"losses":9,"wins":29},"GB2-03":{"draws":3,"losses":15,"wins":56},"GB2-04":{"draws":10,"losses":7,"wins":65},"GB2-05":{"draws":0,"losses":5,"wins":73},"GB2-06":{"draws":8,"losses":8,"wins":80},"GB2-08":{"draws":46,"losses":21,"wins":41}},"medium":{"GB2-01":{"draws":14,"losses":52,"wins":20},"GB2-02":{"draws":73,"losses":15,"wins":12},"GB2-03":{"draws":10,"losses":25,"wins":35},"GB2-04":{"draws":57,"losses":20,"wins":12},"GB2-05":{"draws":0,"losses":55,"wins":37},"GB2-06":{"draws":5,"losses":43,"wins":48},"GB2-07":{"draws":0,"losses":49,"wins":47},"GB2-08":{"draws":46,"losses":38,"wins":20}},"none":{"GB2-01":{"draws":27,"losses":30,"wins":9},"GB2-02":{"draws":77,"losses":20,"wins":5},"GB2-03":{"draws":11,"losses":23,"wins":26},"GB2-04":{"draws":51,"losses":37,"wins":2},"GB2-05":{"draws":0,"losses":30,"wins":56},"GB2-06":{"draws":7,"losses":17,"wins":80},"GB2-07":{"draws":0,"losses":64,"wins":36},"GB2-08":{"draws":65,"losses":34,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1421.684058406747,"GB2-02":1507.1174203215699,"GB2-03":1576.6171448660236,"GB2-04":1520.6309823006338,"GB2-05":1667.2423654319603,"GB2-06":1767.7895661114137,"GB2-08":1414.9800859541301},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1621.2423593102403,"GB2-02":1601.0822501786638,"GB2-03":1669.4909868132202,"GB2-04":1749.9947376670534,"GB2-05":1976.2479871496616,"GB2-06":1869.2664883921934,"GB2-08":1520.8482857750723},"medium":{"GB2-01":1277.1679524023325,"GB2-02":1486.00656718965,"GB2-03":1573.1131892519477,"GB2-04":1461.7875411108187,"GB2-05":1398.1796544837455,"GB2-06":1577.33108070085,"GB2-07":1457.9487742917338,"GB2-08":1381.0241384725944},"none":{"GB2-01":1366.6418635076686,"GB2-02":1434.263443596396,"GB2-03":1487.247258532903,"GB2-04":1350.1106681240292,"GB2-05":1627.2994546624745,"GB2-06":1856.7711292411977,"GB2-07":1375.7779468112376,"GB2-08":1343.0678336147234}},"per_game_tracks":{"highest":{"GB2-01":50.71505113886677,"GB2-02":32.788493526983785,"GB2-03":51.6714073670336,"GB2-04":61.4397821649466,"GB2-05":77.95231468763828,"GB2-06":71.90040976427079,"GB2-08":37.16889411837889},"medium":{"GB2-01":26.064025593310458,"GB2-02":16.666265318883436,"GB2-03":42.514799913936855,"GB2-04":17.499401804482208,"GB2-05":41.81687641086659,"GB2-06":54.2742826878732,"GB2-07":43.40635942789991,"GB2-08":26.265830483916858},"none":{"GB2-01":32.103654711054496,"GB2-02":9.471401049318922,"GB2-03":34.11310533876156,"GB2-04":0.4051207679024251,"GB2-05":56.13873562417903,"GB2-06":71.24124506601923,"GB2-07":38.01897155402717,"GB2-08":23.32133706716388}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.80519325258838,"medium":33.56348020514619,"none":33.10169639730334},"reasoning_agg":{"highest":{"max":77.95231468763828,"mean":54.80519325258838,"min":32.788493526983785},"medium":{"max":54.2742826878732,"mean":33.56348020514619,"min":16.666265318883436},"none":{"max":71.24124506601923,"mean":33.10169639730334,"min":0.4051207679024251}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":77.95231468763828,"expected_score":40.23874623218087,"reasoning_variance":21.70349685528504,"reliability_score":90.42582589023107,"uncertainty_avg":9.574174109768927,"uncertainty_penalty":-0.2513770528317636},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.95231468763828,"expected_score":50.26170584083933,"reliability_score":90.17613415609864,"uncertainty_avg":9.823865843901357,"uncertainty_penalty":-4.543487411749048},"medium":{"ceiling_score":54.2742826878732,"expected_score":35.29528741187341,"reliability_score":91.55269978389191,"uncertainty_avg":8.447300216108083,"uncertainty_penalty":1.7318072067272183},"none":{"ceiling_score":71.24124506601923,"expected_score":37.16630344943843,"reliability_score":90.28357982048078,"uncertainty_avg":9.716420179519213,"uncertainty_penalty":4.064607052135088}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-5:1f9b0e6a5daf3f13","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":4.4173,"mean":2.7356843750000004,"median":2.536595,"min":2.045485,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":21.885475}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":26},"cost_is_complete":false,"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":42.592935685274924,"highest":56.34245228820459,"medium":38.737695472601196,"none":28.751414287560788},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T05:35:58Z","match_totals_all":{"draws":1668,"losses":1209,"wins":1812},"match_totals_tracks":{"highest":{"draws":317,"losses":254,"wins":853},"medium":{"draws":615,"losses":499,"wins":650},"none":{"draws":736,"losses":456,"wins":309}},"model_slug":"gpt-5-5","overall":{"max":83.86214509782288,"mean":40.345926034017175,"min":10.622079152016688},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":26,"overall_ranking_status":"ranked","per_game":{"GB2-01":70.85195136009384,"GB2-03":35.1637334826346,"GB2-04":10.622079152016688,"GB2-05":67.16472233137853,"GB2-06":77.53673555335912,"GB2-07":83.86214509782288,"GB2-08":49.19579904012656},"per_game_all":{"GB2-01":53.535606138979006,"GB2-03":26.265004346867496,"GB2-04":14.188719943694919,"GB2-05":62.89260320289688,"GB2-07":62.54858355448096,"GB2-08":36.1270969247303},"per_game_match_totals_all":{"GB2-01":{"draws":347,"losses":65,"wins":166},"GB2-02":{"draws":347,"losses":48,"wins":49},"GB2-03":{"draws":178,"losses":171,"wins":121},"GB2-04":{"draws":427,"losses":165,"wins":77},"GB2-05":{"draws":0,"losses":167,"wins":371},"GB2-06":{"draws":7,"losses":210,"wins":253},"GB2-07":{"draws":0,"losses":233,"wins":513},"GB2-08":{"draws":362,"losses":150,"wins":262}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":57,"losses":23,"wins":86},"GB2-03":{"draws":52,"losses":51,"wins":57},"GB2-04":{"draws":133,"losses":65,"wins":20},"GB2-05":{"draws":0,"losses":36,"wins":150},"GB2-06":{"draws":5,"losses":23,"wins":164},"GB2-07":{"draws":0,"losses":27,"wins":215},"GB2-08":{"draws":70,"losses":29,"wins":161}},"medium":{"GB2-01":{"draws":132,"losses":7,"wins":63},"GB2-02":{"draws":142,"losses":27,"wins":49},"GB2-03":{"draws":65,"losses":61,"wins":28},"GB2-04":{"draws":153,"losses":49,"wins":32},"GB2-05":{"draws":0,"losses":45,"wins":127},"GB2-06":{"draws":2,"losses":187,"wins":89},"GB2-07":{"draws":0,"losses":69,"wins":171},"GB2-08":{"draws":121,"losses":54,"wins":91}},"none":{"GB2-01":{"draws":158,"losses":35,"wins":17},"GB2-02":{"draws":205,"losses":21,"wins":0},"GB2-03":{"draws":61,"losses":59,"wins":36},"GB2-04":{"draws":141,"losses":51,"wins":25},"GB2-05":{"draws":0,"losses":86,"wins":94},"GB2-07":{"draws":0,"losses":137,"wins":127},"GB2-08":{"draws":171,"losses":67,"wins":10}}},"per_game_raw_elo_all":{"GB2-01":1642.8999842722217,"GB2-03":1384.186406123941,"GB2-04":1424.7781708051923,"GB2-05":1721.5975027636175,"GB2-07":1731.7468701492153,"GB2-08":1493.9684873858212},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1884.3757808905807,"GB2-03":1478.762540193533,"GB2-04":1401.81727314717,"GB2-05":1788.9758093326234,"GB2-06":1950.7977740418642,"GB2-07":2053.9442235076103,"GB2-08":1662.328706977037},"medium":{"GB2-01":1639.8783559612073,"GB2-02":1490.180531205261,"GB2-03":1286.2198647113223,"GB2-04":1465.9393083688733,"GB2-05":1885.6893454361748,"GB2-06":1153.8084958185073,"GB2-07":1706.7874109831719,"GB2-08":1492.9883848232682},"none":{"GB2-01":1404.4458159648777,"GB2-02":1443.7232854519943,"GB2-03":1387.5768134669672,"GB2-04":1406.5779308995332,"GB2-05":1490.1273535220544,"GB2-07":1434.5089759568639,"GB2-08":1326.5883703571585}},"per_game_tracks":{"highest":{"GB2-01":70.85195136009384,"GB2-03":35.1637334826346,"GB2-04":10.622079152016688,"GB2-05":67.16472233137853,"GB2-06":77.53673555335912,"GB2-07":83.86214509782288,"GB2-08":49.19579904012656},"medium":{"GB2-01":53.37347484559559,"GB2-02":19.040412233402826,"GB2-03":17.05444943561178,"GB2-04":20.601271114231235,"GB2-05":73.17445544379497,"GB2-06":29.70961070605602,"GB2-07":60.86711011723705,"GB2-08":36.080779884880066},"none":{"GB2-01":36.3813922112476,"GB2-02":12.599028983400578,"GB2-03":26.576830122356103,"GB2-04":11.342809564836829,"GB2-05":48.33863183351715,"GB2-07":42.91649544838296,"GB2-08":23.10471184918429}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.49262873413381,"medium":38.737695472601196,"none":27.80745389531653},"reasoning_agg":{"highest":{"max":83.86214509782288,"mean":54.49262873413381,"min":10.622079152016688},"medium":{"max":73.17445544379497,"mean":38.737695472601196,"min":17.05444943561178},"none":{"max":48.33863183351715,"mean":27.80745389531653,"min":11.342809564836829}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":83.86214509782288,"expected_score":41.33919315000705,"reasoning_variance":26.68517483881728,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.9932671159898732},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":83.86214509782288,"expected_score":50.04946172029013,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.443167013843677},"medium":{"ceiling_score":73.17445544379497,"expected_score":37.458638650215356,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.27905682238584},"none":{"ceiling_score":48.33863183351715,"expected_score":30.996745474978844,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.1892915796623136}}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k3:588742aa6ac9e321","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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":4.208936999999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.6279041999999999,"mean":0.2975122,"median":0.2990655,"min":0.0550338,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":40},"recorded_attempt_count":40,"run_count":24,"total":7.140292799999999},"codegen_latency_ms":{"attempt_count":40,"max_ms":1201344,"mean_ms":515468.5833333333,"min_ms":64944,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":15,"max_ms":1201344,"mean_ms":973286.5,"min_ms":605299,"run_count":8},"medium":{"attempt_count":16,"max_ms":754602,"mean_ms":479215.25,"min_ms":119309,"run_count":8},"none":{"attempt_count":9,"max_ms":115016,"mean_ms":93904.0,"min_ms":64944,"run_count":8}},"codegen_output_tokens":{"attempt_count":40,"output_max":40000,"output_mean":17970.666666666668,"output_min":2237,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":15,"output_max":40000,"output_mean":33312.25,"output_min":20000,"run_count":8},"medium":{"attempt_count":16,"output_max":27465,"output_mean":17219.125,"output_min":4345,"run_count":8},"none":{"attempt_count":9,"output_max":4534,"output_mean":3380.625,"output_min":2237,"run_count":8}},"display_name":"Kimi K3","economics":{"all":35.662648730424976,"highest":43.12272653950821,"medium":38.53418610349174,"none":42.128267791561626},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T04:25:15Z","match_totals_all":{"draws":2769,"losses":2898,"wins":3291},"match_totals_tracks":{"highest":{"draws":642,"losses":565,"wins":795},"medium":{"draws":1170,"losses":1171,"wins":1069},"none":{"draws":957,"losses":1162,"wins":1427}},"model_slug":"moonshotai-kimi-k3","overall":{"max":88.15806879364996,"mean":40.102051981751906,"min":10.731067494709292},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":27,"overall_ranking_status":"partial","per_game":{"GB2-01":57.11927668502518,"GB2-02":10.731067494709292,"GB2-03":36.877779121239,"GB2-04":54.514956290037006,"GB2-07":56.37055310653056},"per_game_all":{"GB2-01":51.80353040426987,"GB2-02":13.585564745689728,"GB2-03":40.25717937849965,"GB2-04":33.18858957674798,"GB2-07":39.47837954691763},"per_game_match_totals_all":{"GB2-01":{"draws":400,"losses":368,"wins":493},"GB2-02":{"draws":898,"losses":149,"wins":37},"GB2-03":{"draws":393,"losses":339,"wins":411},"GB2-04":{"draws":615,"losses":253,"wins":357},"GB2-05":{"draws":0,"losses":416,"wins":561},"GB2-06":{"draws":87,"losses":440,"wins":463},"GB2-07":{"draws":0,"losses":765,"wins":543},"GB2-08":{"draws":376,"losses":168,"wins":426}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":42,"losses":128,"wins":226},"GB2-02":{"draws":304,"losses":58,"wins":14},"GB2-03":{"draws":184,"losses":118,"wins":92},"GB2-04":{"draws":112,"losses":62,"wins":194},"GB2-07":{"draws":0,"losses":199,"wins":269}},"medium":{"GB2-01":{"draws":60,"losses":123,"wins":173},"GB2-02":{"draws":279,"losses":41,"wins":10},"GB2-03":{"draws":104,"losses":80,"wins":159},"GB2-04":{"draws":308,"losses":71,"wins":60},"GB2-05":{"draws":0,"losses":214,"wins":266},"GB2-06":{"draws":43,"losses":208,"wins":245},"GB2-07":{"draws":0,"losses":290,"wins":128},"GB2-08":{"draws":376,"losses":144,"wins":28}},"none":{"GB2-01":{"draws":298,"losses":117,"wins":94},"GB2-02":{"draws":315,"losses":50,"wins":13},"GB2-03":{"draws":105,"losses":141,"wins":160},"GB2-04":{"draws":195,"losses":120,"wins":103},"GB2-05":{"draws":0,"losses":202,"wins":295},"GB2-06":{"draws":44,"losses":232,"wins":218},"GB2-07":{"draws":0,"losses":276,"wins":146},"GB2-08":{"draws":0,"losses":24,"wins":398}}},"per_game_raw_elo_all":{"GB2-01":1609.7539149364936,"GB2-02":1445.2605047726813,"GB2-03":1522.0696315824844,"GB2-04":1541.7192622759912,"GB2-07":1377.169343367658},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1683.6605057567426,"GB2-02":1424.4424460365362,"GB2-03":1485.6456950792399,"GB2-04":1681.7664481489458,"GB2-07":1631.5859809135386},"medium":{"GB2-01":1730.3739118592769,"GB2-02":1443.7378652036255,"GB2-03":1622.668048440108,"GB2-04":1456.9664548378187,"GB2-05":1563.9597290834351,"GB2-06":1554.54372682174,"GB2-07":1260.5835915333346,"GB2-08":1342.9574897840018},"none":{"GB2-01":1415.2273271934607,"GB2-02":1467.6012030778827,"GB2-03":1457.895151228105,"GB2-04":1486.4248838412093,"GB2-05":1604.0565155662925,"GB2-06":1460.3774398945675,"GB2-07":1239.3384576561007,"GB2-08":2159.265267014722}},"per_game_tracks":{"highest":{"GB2-01":57.11927668502518,"GB2-02":10.731067494709292,"GB2-03":36.877779121239,"GB2-04":54.514956290037006,"GB2-07":56.37055310653056},"medium":{"GB2-01":60.41927960308944,"GB2-02":13.240345043512344,"GB2-03":49.58981828799887,"GB2-04":20.302320214483753,"GB2-05":53.70512763044308,"GB2-06":54.267281427755854,"GB2-07":31.732630638705718,"GB2-08":25.016685981944878},"none":{"GB2-01":37.872034924695,"GB2-02":16.78528169884755,"GB2-03":34.30394072626109,"GB2-04":24.748492225723165,"GB2-05":56.24673344382048,"GB2-06":48.579635623979165,"GB2-07":30.331954895516603,"GB2-08":88.15806879364996}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":39.643702050202336,"medium":38.53418610349174,"none":42.128267791561626},"reasoning_agg":{"highest":{"max":57.11927668502518,"mean":39.643702050202336,"min":10.731067494709292},"medium":{"max":60.41927960308944,"mean":38.53418610349174,"min":13.240345043512344},"none":{"max":88.15806879364996,"mean":42.128267791561626,"min":16.78528169884755}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":88.15806879364996,"expected_score":34.45385720841532,"reasoning_variance":3.5940816880698847,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.648194773336584},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":57.11927668502518,"expected_score":36.57189265923168,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.0718093909706568},"medium":{"ceiling_score":60.41927960308944,"expected_score":38.45894339674897,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.07524270674277034},"none":{"ceiling_score":88.15806879364996,"expected_score":45.694421666809404,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.566153875247778}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1-nano:27769ccf83edf63d","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":1,"cell_count":1,"cost_basis_counts":{"estimated":1,"local_standard_estimate":1},"cost_is_complete":false,"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-2026-09-08":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},"cost_is_complete":false,"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-2026-09-08":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},"cost_is_complete":false,"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-2026-09-08":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":40.0701195430489},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T04:34:15Z","match_totals_all":{"draws":75,"losses":169,"wins":162},"match_totals_tracks":{"none":{"draws":75,"losses":169,"wins":162}},"model_slug":"gpt-4-1-nano","overall":{"max":40.0701195430489,"mean":40.0701195430489,"min":40.0701195430489},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":28,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":75,"losses":169,"wins":162}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":75,"losses":169,"wins":162}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1447.7281790652517}},"per_game_tracks":{"none":{"GB2-01":40.0701195430489}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":40.0701195430489},"reasoning_agg":{"none":{"max":40.0701195430489,"mean":40.0701195430489,"min":40.0701195430489}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"},"score_diagnostics":{"ceiling_score":40.0701195430489},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":40.0701195430489,"expected_score":43.0425064060681,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.972386863019203}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-spark-1-2:24ca876a504f091c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":2,"cell_count":2,"cost_basis_counts":{"provider_reported":2},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.37616800000000006},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.8154702500000002},"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":44.07703586858476,"highest":47.14305346291842,"medium":41.57939422404137,"none":31.876968355943443},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T06:59:40Z","match_totals_all":{"draws":1436,"losses":2429,"wins":2461},"match_totals_tracks":{"highest":{"draws":97,"losses":307,"wins":378},"medium":{"draws":632,"losses":808,"wins":1154},"none":{"draws":707,"losses":1314,"wins":929}},"model_slug":"meta-muse-spark-1-2","overall":{"max":73.96293697489726,"mean":39.74476336965902,"min":10.33428865358141},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":29,"overall_ranking_status":"partial","per_game":{"GB2-01":52.57001535461252,"GB2-03":41.716091571224304},"per_game_all":{"GB2-01":54.23122727883316,"GB2-03":33.92284445833635},"per_game_match_totals_all":{"GB2-01":{"draws":193,"losses":332,"wins":553},"GB2-02":{"draws":492,"losses":115,"wins":34},"GB2-03":{"draws":237,"losses":475,"wins":465},"GB2-04":{"draws":437,"losses":138,"wins":107},"GB2-05":{"draws":0,"losses":412,"wins":424},"GB2-06":{"draws":3,"losses":281,"wins":78},"GB2-07":{"draws":0,"losses":388,"wins":376},"GB2-08":{"draws":74,"losses":288,"wins":424}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":37,"losses":146,"wins":201},"GB2-03":{"draws":60,"losses":161,"wins":177}},"medium":{"GB2-01":{"draws":13,"losses":63,"wins":280},"GB2-02":{"draws":257,"losses":57,"wins":27},"GB2-03":{"draws":116,"losses":142,"wins":127},"GB2-04":{"draws":181,"losses":78,"wins":55},"GB2-05":{"draws":0,"losses":211,"wins":209},"GB2-07":{"draws":0,"losses":148,"wins":230},"GB2-08":{"draws":65,"losses":109,"wins":226}},"none":{"GB2-01":{"draws":143,"losses":123,"wins":72},"GB2-02":{"draws":235,"losses":58,"wins":7},"GB2-03":{"draws":61,"losses":172,"wins":161},"GB2-04":{"draws":256,"losses":60,"wins":52},"GB2-05":{"draws":0,"losses":201,"wins":215},"GB2-06":{"draws":3,"losses":281,"wins":78},"GB2-07":{"draws":0,"losses":240,"wins":146},"GB2-08":{"draws":9,"losses":179,"wins":198}}},"per_game_raw_elo_all":{"GB2-01":1644.7549760073714,"GB2-03":1454.1734849693685},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1621.0828827553369,"GB2-03":1537.1482374204795},"medium":{"GB2-01":1917.59874451867,"GB2-02":1475.5657711271901,"GB2-03":1413.9369042511964,"GB2-04":1402.9682859613501,"GB2-05":1496.8238098495474,"GB2-07":1668.5697447646592,"GB2-08":1663.2381625175155},"none":{"GB2-01":1395.5833007481067,"GB2-02":1424.0649249590012,"GB2-03":1411.4353132364292,"GB2-04":1462.2759851652143,"GB2-05":1553.238278634504,"GB2-06":1045.3432882066063,"GB2-07":1314.1256384076203,"GB2-08":1619.8321883127128}},"per_game_tracks":{"highest":{"GB2-01":52.57001535461252,"GB2-03":41.716091571224304},"medium":{"GB2-01":73.96293697489726,"GB2-02":17.749410457098115,"GB2-03":30.13255826814618,"GB2-04":11.487658141173375,"GB2-05":49.403646108374964,"GB2-07":58.68205007707015,"GB2-08":49.63749954152954},"none":{"GB2-01":36.16072950698971,"GB2-02":10.33428865358141,"GB2-03":29.919883535638572,"GB2-04":20.84770942175147,"GB2-05":52.94592467488847,"GB2-06":23.33910979357626,"GB2-07":35.22563758767662,"GB2-08":46.24246367344504}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.14305346291842,"medium":40.21426829011519,"none":31.876968355943443},"reasoning_agg":{"highest":{"max":52.57001535461252,"mean":47.14305346291842,"min":41.716091571224304},"medium":{"max":73.96293697489726,"mean":40.21426829011519,"min":11.487658141173375},"none":{"max":52.94592467488847,"mean":31.876968355943443,"min":10.33428865358141}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":73.96293697489726,"expected_score":41.39956423102482,"reasoning_variance":15.266085106974973,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.6548008613657998},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":52.57001535461252,"expected_score":39.130407119271595,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.012646343646821},"medium":{"ceiling_score":73.96293697489726,"expected_score":41.96746016483945,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7531918747242585},"none":{"ceiling_score":52.94592467488847,"expected_score":32.86299709973343,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.9860287437899835}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-1-flash:b9ebacea37464f0c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.02640173625,"median":0.026524292999999997,"min":0.018252918,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.21121389},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0294003,"mean":0.0190911675,"median":0.019388559,"min":0.011042118,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.15272934000000002},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.007391933999999999,"mean":0.00359850675,"median":0.003217359,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.028788053999999997}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0294003,"mean":0.0190911675,"median":0.019388559,"min":0.011042118,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.15272934000000002},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.007391933999999999,"mean":0.00359850675,"median":0.003217359,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":9},"recorded_attempt_count":9,"run_count":8,"total":0.028788053999999997},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.02640173625,"median":0.026524292999999997,"min":0.018252918,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.21121389}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.031583268,"mean":0.0163638035,"median":0.017740284000000002,"min":0.00220635,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":26},"recorded_attempt_count":26,"run_count":24,"total":0.3927312839999999},"codegen_latency_ms":{"attempt_count":26,"max_ms":176041,"mean_ms":89449.0,"min_ms":6041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":176041,"mean_ms":153558.625,"min_ms":128316,"run_count":8},"medium":{"attempt_count":9,"max_ms":152315,"mean_ms":102702.875,"min_ms":61501,"run_count":8},"none":{"attempt_count":9,"max_ms":25470,"mean_ms":12085.5,"min_ms":6041,"run_count":8}},"codegen_output_tokens":{"attempt_count":26,"output_max":50785,"output_mean":25087.541666666668,"output_min":1796,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":50785,"output_mean":42017.75,"output_min":28632,"run_count":8},"medium":{"attempt_count":9,"output_max":44567,"output_mean":29519.625,"output_min":16614,"run_count":8},"none":{"attempt_count":9,"output_max":8282,"output_mean":3725.25,"output_min":1796,"run_count":8}},"display_name":"DeepSeek V4.1 Flash","economics":{"all":39.52711275456211,"highest":53.454286399681976,"medium":40.32854572881491,"none":24.798506135189438},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":26,"effective_max_output_tokens":[384000],"finish_reason_observations":26,"finish_reasons":["stop"],"indexed_attempts":26,"output_token_observations":26,"provider_post_attempt_observations":26,"provider_post_attempts":26,"reasoning_token_observations":26,"reconciliation_get_attempt_observations":26,"requested_max_output_token_observations":26,"requested_max_output_tokens":[384000],"total_output_tokens":602101,"total_reasoning_output_tokens":512212,"total_visible_output_tokens":89889,"visible_token_observations":26},"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":384000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"deepseek","provider_model":"deepseek/deepseek-v4.1-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"deepseek/deepseek-v4.1-flash","is_recent_addition":false,"last_measured_at":"2026-09-26T06:33:37Z","match_totals_all":{"draws":624,"losses":685,"wins":861},"match_totals_tracks":{"highest":{"draws":147,"losses":129,"wins":438},"medium":{"draws":216,"losses":206,"wins":292},"none":{"draws":261,"losses":350,"wins":131}},"model_slug":"deepseek-deepseek-v4-1-flash","overall":{"max":77.62403711318424,"mean":39.52711275456211,"min":8.791454303397531},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":30,"overall_ranking_status":"ranked","per_game":{"GB2-01":50.61811252326289,"GB2-02":31.120166136562638,"GB2-03":39.817741705723044,"GB2-04":51.88718266652062,"GB2-05":73.41826598272793,"GB2-06":77.62403711318424,"GB2-07":64.22140156356532,"GB2-08":38.92738350590912},"per_game_all":{"GB2-01":49.14593618428853,"GB2-02":22.08530579069524,"GB2-03":33.60245019935162,"GB2-04":24.974256294234664,"GB2-05":51.78703023443497,"GB2-06":60.49548251823803,"GB2-07":49.58115007523239,"GB2-08":24.545290740021418},"per_game_match_totals_all":{"GB2-01":{"draws":67,"losses":71,"wins":98},"GB2-02":{"draws":215,"losses":30,"wins":51},"GB2-03":{"draws":38,"losses":77,"wins":85},"GB2-04":{"draws":123,"losses":66,"wins":77},"GB2-05":{"draws":0,"losses":117,"wins":137},"GB2-06":{"draws":20,"losses":85,"wins":185},"GB2-07":{"draws":0,"losses":115,"wins":183},"GB2-08":{"draws":161,"losses":124,"wins":45}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":30,"wins":50},"GB2-02":{"draws":59,"losses":8,"wins":27},"GB2-03":{"draws":6,"losses":24,"wins":34},"GB2-04":{"draws":26,"losses":8,"wins":54},"GB2-05":{"draws":0,"losses":9,"wins":73},"GB2-06":{"draws":6,"losses":8,"wins":84},"GB2-07":{"draws":0,"losses":16,"wins":80},"GB2-08":{"draws":50,"losses":26,"wins":36}},"medium":{"GB2-01":{"draws":46,"losses":6,"wins":22},"GB2-02":{"draws":65,"losses":7,"wins":24},"GB2-03":{"draws":12,"losses":22,"wins":32},"GB2-04":{"draws":42,"losses":34,"wins":16},"GB2-05":{"draws":0,"losses":44,"wins":38},"GB2-06":{"draws":10,"losses":7,"wins":79},"GB2-07":{"draws":0,"losses":25,"wins":77},"GB2-08":{"draws":41,"losses":61,"wins":4}},"none":{"GB2-01":{"draws":21,"losses":35,"wins":26},"GB2-02":{"draws":91,"losses":15,"wins":0},"GB2-03":{"draws":20,"losses":31,"wins":19},"GB2-04":{"draws":55,"losses":24,"wins":7},"GB2-05":{"draws":0,"losses":64,"wins":26},"GB2-06":{"draws":4,"losses":70,"wins":22},"GB2-07":{"draws":0,"losses":74,"wins":26},"GB2-08":{"draws":70,"losses":37,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1598.2092605891905,"GB2-02":1524.992063229025,"GB2-03":1479.2370240085193,"GB2-04":1510.6096142539743,"GB2-05":1558.47171268699,"GB2-06":1680.2332034311737,"GB2-07":1550.5273156508263,"GB2-08":1357.7850450800443},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1618.1587220285023,"GB2-02":1590.4118705778744,"GB2-03":1546.4899755624251,"GB2-04":1686.2116710527107,"GB2-05":1903.0601287374295,"GB2-06":1963.6526019708674,"GB2-07":1772.2903418984033,"GB2-08":1542.8320631621687},"medium":{"GB2-01":1701.0790808886545,"GB2-02":1536.4870574940828,"GB2-03":1501.9419324906219,"GB2-04":1439.8794795650863,"GB2-05":1488.5916793717895,"GB2-06":1882.1384855412623,"GB2-07":1690.7518283863521,"GB2-08":1217.7530715265236},"none":{"GB2-01":1475.3899788504148,"GB2-02":1448.077261615118,"GB2-03":1389.2791639725108,"GB2-04":1405.7376921441253,"GB2-05":1283.7633299517513,"GB2-06":1194.9085227813916,"GB2-07":1188.5397766677231,"GB2-08":1312.7700005514405}},"per_game_tracks":{"highest":{"GB2-01":50.61811252326289,"GB2-02":31.120166136562638,"GB2-03":39.817741705723044,"GB2-04":51.88718266652062,"GB2-05":73.41826598272793,"GB2-06":77.62403711318424,"GB2-07":64.22140156356532,"GB2-08":38.92738350590912},"medium":{"GB2-01":56.490359827290426,"GB2-02":23.624824475865857,"GB2-03":35.71091424038222,"GB2-04":14.244131912785832,"GB2-05":47.350587701601285,"GB2-06":72.67757982141026,"GB2-07":58.90159770662399,"GB2-08":13.62837014455938},"none":{"GB2-01":40.32933620231229,"GB2-02":11.510926759657222,"GB2-03":25.278694651949607,"GB2-04":8.791454303397531,"GB2-05":34.592237018975695,"GB2-06":31.184830620119577,"GB2-07":25.620450955507845,"GB2-08":21.080118569595758}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":53.454286399681976,"medium":40.32854572881491,"none":24.798506135189438},"reasoning_agg":{"highest":{"max":77.62403711318424,"mean":53.454286399681976,"min":31.120166136562638},"medium":{"max":72.67757982141026,"mean":40.32854572881491,"min":13.62837014455938},"none":{"max":40.32933620231229,"mean":24.798506135189438,"min":8.791454303397531}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":77.62403711318424,"expected_score":39.70979539806319,"reasoning_variance":28.655780264492538,"reliability_score":91.01543363700374,"uncertainty_avg":8.984566362996265,"uncertainty_penalty":0.18268264350108154},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.62403711318424,"expected_score":48.88064050194356,"reliability_score":90.64886163894974,"uncertainty_avg":9.35113836105026,"uncertainty_penalty":-4.573645897738416},"medium":{"ceiling_score":72.67757982141026,"expected_score":42.9440685798651,"reliability_score":90.66407891220733,"uncertainty_avg":9.33592108779267,"uncertainty_penalty":2.615522851050194},"none":{"ceiling_score":40.32933620231229,"expected_score":27.304677112380908,"reliability_score":91.73336035985413,"uncertainty_avg":8.266639640145867,"uncertainty_penalty":2.50617097719147}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-max:0a2909a34622f950","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.3468699583333334,"median":0.3476285,"min":0.237408,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":13,"total":4.659586000000001},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.25803,"mean":0.104435,"median":0.081263,"min":0.075542,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"recorded_attempt_count":8,"run_count":8,"total":0.83548},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":8},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.40721066666666667,"mean":0.19033848611111112,"median":0.13741799999999998,"min":0.066054,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":30},"recorded_attempt_count":30,"run_count":29,"total":6.452750000000002},"codegen_latency_ms":{"attempt_count":30,"max_ms":1708792,"mean_ms":723489.2413793104,"min_ms":155474,"run_count":29},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":1708792,"mean_ms":1260718.7692307692,"min_ms":853424,"run_count":13},"medium":{"attempt_count":8,"max_ms":700604,"mean_ms":265043.125,"min_ms":183145,"run_count":8},"none":{"attempt_count":8,"max_ms":461859,"mean_ms":308937.375,"min_ms":155474,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":76211,"output_mean":34293.10344827586,"output_min":8500,"run_count":29},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":76211,"output_mean":56804.769230769234,"output_min":37117,"run_count":13},"medium":{"attempt_count":8,"output_max":40473,"output_mean":14733.75,"output_min":10090,"run_count":8},"none":{"attempt_count":8,"output_max":26415,"output_mean":17271.0,"output_min":8500,"run_count":8}},"display_name":"Qwen3.8 Max","economics":{"all":38.745946458753004,"highest":41.679786501665475,"medium":38.58328878858141,"none":35.97476408601212},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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":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/qwen3.8-max","is_recent_addition":false,"last_measured_at":"2026-09-26T05:37:05Z","match_totals_all":{"draws":2090,"losses":2373,"wins":2356},"match_totals_tracks":{"highest":{"draws":635,"losses":816,"wins":889},"medium":{"draws":703,"losses":845,"wins":769},"none":{"draws":752,"losses":712,"wins":698}},"model_slug":"qwen-qwen3-8-max","overall":{"max":90.85127381485019,"mean":37.9921204078625,"min":11.60119326326969},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":31,"overall_ranking_status":"ranked","per_game":{"GB2-01":29.48138836622312,"GB2-02":20.585364287520385,"GB2-03":48.11571581076036,"GB2-04":41.66722966224277,"GB2-05":43.48045619656421,"GB2-06":51.49191062883913,"GB2-07":68.06335502628858,"GB2-08":30.552872034885215},"per_game_all":{"GB2-01":30.381347196100737,"GB2-02":14.849132105536489,"GB2-03":40.68450041178364,"GB2-04":22.764210746727016,"GB2-05":65.81453814422694,"GB2-06":40.93545688458361,"GB2-07":55.88419570873965,"GB2-08":38.65419047232594},"per_game_match_totals_all":{"GB2-01":{"draws":228,"losses":402,"wins":166},"GB2-02":{"draws":646,"losses":104,"wins":44},"GB2-03":{"draws":228,"losses":262,"wins":276},"GB2-04":{"draws":486,"losses":149,"wins":145},"GB2-05":{"draws":0,"losses":300,"wins":517},"GB2-06":{"draws":80,"losses":533,"wins":376},"GB2-07":{"draws":0,"losses":337,"wins":522},"GB2-08":{"draws":422,"losses":286,"wins":310}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":51,"losses":123,"wins":56},"GB2-02":{"draws":202,"losses":30,"wins":33},"GB2-03":{"draws":33,"losses":98,"wins":120},"GB2-04":{"draws":106,"losses":39,"wins":102},"GB2-05":{"draws":0,"losses":183,"wins":143},"GB2-06":{"draws":32,"losses":172,"wins":171},"GB2-07":{"draws":0,"losses":70,"wins":202},"GB2-08":{"draws":211,"losses":101,"wins":62}},"medium":{"GB2-01":{"draws":111,"losses":125,"wins":74},"GB2-02":{"draws":236,"losses":47,"wins":3},"GB2-03":{"draws":74,"losses":86,"wins":96},"GB2-04":{"draws":200,"losses":64,"wins":13},"GB2-05":{"draws":0,"losses":99,"wins":143},"GB2-06":{"draws":27,"losses":164,"wins":163},"GB2-07":{"draws":0,"losses":169,"wins":139},"GB2-08":{"draws":55,"losses":91,"wins":138}},"none":{"GB2-01":{"draws":66,"losses":154,"wins":36},"GB2-02":{"draws":208,"losses":27,"wins":8},"GB2-03":{"draws":121,"losses":78,"wins":60},"GB2-04":{"draws":180,"losses":46,"wins":30},"GB2-05":{"draws":0,"losses":18,"wins":231},"GB2-06":{"draws":21,"losses":197,"wins":42},"GB2-07":{"draws":0,"losses":98,"wins":181},"GB2-08":{"draws":156,"losses":94,"wins":110}}},"per_game_raw_elo_all":{"GB2-01":1318.615682138936,"GB2-02":1457.8163226815484,"GB2-03":1531.1059122483819,"GB2-04":1478.7278496919153,"GB2-05":1762.6168071948887,"GB2-06":1337.9967714708234,"GB2-07":1629.3938553179003,"GB2-08":1523.4824372592436},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1307.842463828963,"GB2-02":1498.7040191678889,"GB2-03":1610.5768848419052,"GB2-04":1602.5837547507494,"GB2-05":1405.272068563786,"GB2-06":1511.2621990590883,"GB2-07":1813.9054490830777,"GB2-08":1417.9066107874146},"medium":{"GB2-01":1458.0987942293034,"GB2-02":1433.6633510264687,"GB2-03":1564.8159771164214,"GB2-04":1414.687398706827,"GB2-05":1720.9459886496036,"GB2-06":1503.805806278319,"GB2-07":1353.1974872111125,"GB2-08":1642.89446494067},"none":{"GB2-01":1189.9057883585415,"GB2-02":1441.0815978502872,"GB2-03":1417.9248747868187,"GB2-04":1418.9123956181697,"GB2-05":2161.632364371277,"GB2-06":998.9223090750629,"GB2-07":1721.0786296595109,"GB2-08":1509.6462360496457}},"per_game_tracks":{"highest":{"GB2-01":29.48138836622312,"GB2-02":20.585364287520385,"GB2-03":48.11571581076036,"GB2-04":41.66722966224277,"GB2-05":43.48045619656421,"GB2-06":51.49191062883913,"GB2-07":68.06335502628858,"GB2-08":30.552872034885215},"medium":{"GB2-01":40.61381657892143,"GB2-02":11.60119326326969,"GB2-03":43.84831061050232,"GB2-04":13.06236498296679,"GB2-05":63.1118844212664,"GB2-06":51.00540861300187,"GB2-07":37.652509913894924,"GB2-08":47.77082192482787},"none":{"GB2-01":21.048836643157667,"GB2-02":12.360838765819386,"GB2-03":30.08947481408825,"GB2-04":13.563037594971485,"GB2-05":90.85127381485019,"GB2-06":20.30905141190983,"GB2-07":61.93672218603544,"GB2-08":37.63887745726475}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":39.41830834899395,"medium":38.58328878858141,"none":35.97476408601212},"reasoning_agg":{"highest":{"max":68.06335502628858,"mean":39.41830834899395,"min":20.585364287520385},"medium":{"max":63.1118844212664,"mean":38.58328878858141,"min":11.60119326326969},"none":{"max":90.85127381485019,"mean":35.97476408601212,"min":12.360838765819386}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":90.85127381485019,"expected_score":36.32341161437176,"reasoning_variance":3.443544262981831,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.6687087934907439},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":68.06335502628858,"expected_score":32.95793714238712,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.460371206606837},"medium":{"ceiling_score":63.1118844212664,"expected_score":38.86332652662958,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.2800377380481649},"none":{"ceiling_score":90.85127381485019,"expected_score":37.14897117409856,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.1742070880864404}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-sonnet-5:2e363afacad82877","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.35099375,"median":0.321349,"min":0.220732,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":2.80795},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.52499},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.07847,"mean":0.06167125,"median":0.061313,"min":0.051588,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.49337}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.08884,"mean":0.06562375000000001,"median":0.062855,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.52499},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"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-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"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":2.8079499999999995}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_list_price_estimate":24},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.50466,"mean":0.15942958333333332,"median":0.068377,"min":0.049908,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":24},"run_count":24,"token_priced_attempt_count":24,"total":3.8263099999999994},"codegen_output_tokens":{"attempt_count":24,"output_max":47973,"output_mean":13430.583333333334,"output_min":2639,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":47973,"output_mean":32587.0,"output_min":19731,"run_count":8},"medium":{"attempt_count":8,"output_max":5918,"output_mean":4050.0,"output_min":2639,"run_count":8},"none":{"attempt_count":8,"output_max":4635,"output_mean":3654.75,"output_min":2807,"run_count":8}},"display_name":"Claude Sonnet 5","economics":{"all":37.55693808331602,"highest":45.760425682163365,"medium":35.2500499727137,"none":31.660338595071003},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[128000],"finish_reason_observations":24,"finish_reasons":["end_turn"],"indexed_attempts":24,"output_token_observations":24,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":24,"reconciliation_get_attempt_observations":24,"requested_max_output_token_observations":24,"requested_max_output_tokens":[128000],"total_output_tokens":322334,"total_reasoning_output_tokens":243107,"total_visible_output_tokens":79227,"visible_token_observations":24},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"end_turn","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":128000,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"anthropic","provider_model":"claude-sonnet-5","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"anthropic","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"claude-sonnet-5","is_recent_addition":false,"last_measured_at":"2026-09-26T07:08:14Z","match_totals_all":{"draws":2487,"losses":3344,"wins":2990},"match_totals_tracks":{"highest":{"draws":626,"losses":931,"wins":1180},"medium":{"draws":964,"losses":1183,"wins":917},"none":{"draws":897,"losses":1230,"wins":893}},"model_slug":"claude-sonnet-5","overall":{"max":64.32072153807952,"mean":37.55693808331603,"min":13.284681007236937},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":32,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.57869643611395,"GB2-02":14.813507260567727,"GB2-03":44.73199595413562,"GB2-04":34.81547191773764,"GB2-05":52.32673117803436,"GB2-06":37.912905858175336,"GB2-07":58.58337531446278,"GB2-08":64.32072153807952},"per_game_all":{"GB2-01":47.715972115599016,"GB2-02":13.98444382109779,"GB2-03":37.83543744906128,"GB2-04":24.498807772873334,"GB2-05":44.8394894872417,"GB2-06":41.48906462864167,"GB2-07":47.562209509057446,"GB2-08":42.53007988295591},"per_game_match_totals_all":{"GB2-01":{"draws":178,"losses":503,"wins":508},"GB2-02":{"draws":859,"losses":128,"wins":21},"GB2-03":{"draws":370,"losses":399,"wins":310},"GB2-04":{"draws":601,"losses":205,"wins":197},"GB2-05":{"draws":0,"losses":586,"wins":464},"GB2-06":{"draws":61,"losses":601,"wins":450},"GB2-07":{"draws":0,"losses":583,"wins":601},"GB2-08":{"draws":418,"losses":339,"wins":439}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":49,"losses":132,"wins":229},"GB2-02":{"draws":268,"losses":29,"wins":5},"GB2-03":{"draws":107,"losses":115,"wins":97},"GB2-04":{"draws":182,"losses":66,"wins":96},"GB2-05":{"draws":0,"losses":161,"wins":179},"GB2-06":{"draws":18,"losses":216,"wins":98},"GB2-07":{"draws":0,"losses":133,"wins":213},"GB2-08":{"draws":2,"losses":79,"wins":263}},"medium":{"GB2-01":{"draws":67,"losses":172,"wins":136},"GB2-02":{"draws":292,"losses":47,"wins":9},"GB2-03":{"draws":119,"losses":157,"wins":98},"GB2-04":{"draws":208,"losses":87,"wins":58},"GB2-05":{"draws":0,"losses":200,"wins":188},"GB2-06":{"draws":22,"losses":174,"wins":150},"GB2-07":{"draws":0,"losses":212,"wins":226},"GB2-08":{"draws":256,"losses":134,"wins":52}},"none":{"GB2-01":{"draws":62,"losses":199,"wins":143},"GB2-02":{"draws":299,"losses":52,"wins":7},"GB2-03":{"draws":144,"losses":127,"wins":115},"GB2-04":{"draws":211,"losses":52,"wins":43},"GB2-05":{"draws":0,"losses":225,"wins":97},"GB2-06":{"draws":21,"losses":211,"wins":202},"GB2-07":{"draws":0,"losses":238,"wins":162},"GB2-08":{"draws":160,"losses":126,"wins":124}}},"per_game_raw_elo_all":{"GB2-01":1553.6740408847816,"GB2-02":1448.8970669250364,"GB2-03":1496.8501239153265,"GB2-04":1487.1305580315156,"GB2-05":1426.1597875655873,"GB2-06":1345.8172915333823,"GB2-07":1500.274848428291,"GB2-08":1571.7342999110426},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1703.4903552874227,"GB2-02":1455.960041686246,"GB2-03":1571.6504086685761,"GB2-04":1554.0496124922547,"GB2-05":1545.4664135662097,"GB2-06":1287.6493094963394,"GB2-07":1668.0060978319893,"GB2-08":1854.0740231502132},"medium":{"GB2-01":1514.2672333146945,"GB2-02":1447.5516327649157,"GB2-03":1434.5089135352096,"GB2-04":1435.785836843,"GB2-05":1535.3883772720833,"GB2-06":1408.0761809218207,"GB2-07":1521.2844593085858,"GB2-08":1390.4705110471327},"none":{"GB2-01":1443.2645340522272,"GB2-02":1443.179526323947,"GB2-03":1484.3910495421942,"GB2-04":1471.5562247592927,"GB2-05":1197.6245718584694,"GB2-06":1341.7263841819865,"GB2-07":1311.5339881442974,"GB2-08":1470.6583655357822}},"per_game_tracks":{"highest":{"GB2-01":58.57869643611395,"GB2-02":14.813507260567727,"GB2-03":44.73199595413562,"GB2-04":34.81547191773764,"GB2-05":52.32673117803436,"GB2-06":37.912905858175336,"GB2-07":58.58337531446278,"GB2-08":64.32072153807952},"medium":{"GB2-01":44.82553307077868,"GB2-02":13.855143195488708,"GB2-03":32.033575890700774,"GB2-04":16.71746522965975,"GB2-05":51.779700540255305,"GB2-06":45.210868274185785,"GB2-07":49.025516928199515,"GB2-08":28.552596652441004},"none":{"GB2-01":39.74368683990443,"GB2-02":13.284681007236937,"GB2-03":36.740740502347464,"GB2-04":21.96348617122262,"GB2-05":30.412036743435426,"GB2-06":41.3434197535639,"GB2-07":35.07773628451004,"GB2-08":34.716921458347194}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":45.760425682163365,"medium":35.2500499727137,"none":31.660338595071003},"reasoning_agg":{"highest":{"max":64.32072153807952,"mean":45.760425682163365,"min":14.813507260567727},"medium":{"max":51.779700540255305,"mean":35.2500499727137,"min":13.855143195488708},"none":{"max":41.3434197535639,"mean":31.660338595071003,"min":13.284681007236937}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":64.32072153807952,"expected_score":34.96759317407643,"reasoning_variance":14.100087087092362,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.5893449092395997},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":64.32072153807952,"expected_score":37.68624157170314,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.074184110460223},"medium":{"ceiling_score":51.779700540255305,"expected_score":33.933080046814304,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.316969925899393},"none":{"ceiling_score":41.3434197535639,"expected_score":33.28345790371185,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.6231193086408453}}},{"canonical_public_row_identity":"publication-row.v1:overall:claude-opus-4-5:e04fe29aa9cb387c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":17},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":1.42452},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":8},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.512955,"mean":0.2537023958333333,"median":0.20905875000000002,"min":0.09594,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":16,"boardgame-list-prices-2026-08-08":25},"run_count":40,"token_priced_attempt_count":41,"total":11.203785},"codegen_latency_ms":{"attempt_count":24,"max_ms":319301,"mean_ms":98881.45833333333,"min_ms":22230,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":319301,"mean_ms":209645.0,"min_ms":137590,"run_count":8},"medium":{"attempt_count":8,"max_ms":81353,"mean_ms":54764.0,"min_ms":30922,"run_count":8},"none":{"attempt_count":8,"max_ms":40585,"mean_ms":32235.375,"min_ms":22230,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27669,"output_mean":9998.125,"output_min":2138,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":27669,"output_mean":21703.125,"output_min":14720,"run_count":8},"medium":{"attempt_count":8,"output_max":8008,"output_mean":5259.0,"output_min":2375,"run_count":8},"none":{"attempt_count":8,"output_max":4031,"output_mean":3032.25,"output_min":2138,"run_count":8}},"display_name":"Claude Opus 4.5","economics":{"all":36.983107845768586,"highest":35.062840543996515,"medium":39.69082008070261,"none":36.19566291260662},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"claude-opus-4-5","is_recent_addition":false,"last_measured_at":"2026-09-26T07:10:17Z","match_totals_all":{"draws":2371,"losses":3136,"wins":3131},"match_totals_tracks":{"highest":{"draws":997,"losses":1335,"wins":1190},"medium":{"draws":814,"losses":1202,"wins":1338},"none":{"draws":560,"losses":599,"wins":603}},"model_slug":"claude-opus-4-5","overall":{"max":65.9586238785346,"mean":36.98310784576858,"min":9.440431376403948},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":33,"overall_ranking_status":"ranked","per_game":{"GB2-01":58.702268945584024,"GB2-02":11.9006124570664,"GB2-03":24.333522158958257,"GB2-04":11.105048672649573,"GB2-05":47.672224676332476,"GB2-06":58.98721041188529,"GB2-07":41.98521707144406,"GB2-08":25.816619958052044},"per_game_all":{"GB2-01":47.849129733609146,"GB2-02":12.69546454680586,"GB2-03":29.145145231639905,"GB2-04":15.85106430806366,"GB2-05":47.55398577688313,"GB2-06":49.406854167303486,"GB2-07":41.50606588824194,"GB2-08":51.857153113601534},"per_game_match_totals_all":{"GB2-01":{"draws":322,"losses":299,"wins":438},"GB2-02":{"draws":810,"losses":162,"wins":26},"GB2-03":{"draws":335,"losses":343,"wins":237},"GB2-04":{"draws":539,"losses":217,"wins":116},"GB2-05":{"draws":0,"losses":531,"wins":597},"GB2-06":{"draws":89,"losses":538,"wins":587},"GB2-07":{"draws":0,"losses":692,"wins":592},"GB2-08":{"draws":276,"losses":354,"wins":538}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":56,"losses":106,"wins":197},"GB2-02":{"draws":305,"losses":60,"wins":11},"GB2-03":{"draws":99,"losses":153,"wins":126},"GB2-04":{"draws":246,"losses":142,"wins":55},"GB2-05":{"draws":0,"losses":232,"wins":246},"GB2-06":{"draws":35,"losses":196,"wins":253},"GB2-07":{"draws":0,"losses":249,"wins":253},"GB2-08":{"draws":256,"losses":197,"wins":49}},"medium":{"GB2-01":{"draws":138,"losses":133,"wins":199},"GB2-02":{"draws":308,"losses":67,"wins":5},"GB2-03":{"draws":150,"losses":129,"wins":82},"GB2-04":{"draws":172,"losses":37,"wins":20},"GB2-05":{"draws":0,"losses":216,"wins":240},"GB2-06":{"draws":41,"losses":229,"wins":240},"GB2-07":{"draws":0,"losses":295,"wins":227},"GB2-08":{"draws":5,"losses":96,"wins":325}},"none":{"GB2-01":{"draws":128,"losses":60,"wins":42},"GB2-02":{"draws":197,"losses":35,"wins":10},"GB2-03":{"draws":86,"losses":61,"wins":29},"GB2-04":{"draws":121,"losses":38,"wins":41},"GB2-05":{"draws":0,"losses":83,"wins":111},"GB2-06":{"draws":13,"losses":113,"wins":94},"GB2-07":{"draws":0,"losses":148,"wins":112},"GB2-08":{"draws":15,"losses":61,"wins":164}}},"per_game_raw_elo_all":{"GB2-01":1557.3800574790075,"GB2-02":1440.1139083868545,"GB2-03":1406.924717000206,"GB2-04":1433.4017248643358,"GB2-05":1469.7973692789558,"GB2-06":1477.0213544795527,"GB2-07":1408.6657770807972,"GB2-08":1692.8620424195944},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1706.5499032646053,"GB2-02":1432.7903110830057,"GB2-03":1352.2736517275232,"GB2-04":1396.919612485389,"GB2-05":1468.0763755610644,"GB2-06":1632.9388799406668,"GB2-07":1413.7084457933224,"GB2-08":1354.032658083545},"medium":{"GB2-01":1586.0348156078949,"GB2-02":1429.961299453459,"GB2-03":1494.9608055649658,"GB2-04":1393.459354936506,"GB2-05":1470.8552672837006,"GB2-06":1455.8197528554633,"GB2-07":1516.0688010199037,"GB2-08":1845.1349031177228},"none":{"GB2-01":1379.5554535645226,"GB2-02":1457.5901146240985,"GB2-03":1373.539693708129,"GB2-04":1509.8262071711129,"GB2-05":1470.460464992102,"GB2-06":1342.3054306425279,"GB2-07":1296.2200844291658,"GB2-08":1879.418566057516}},"per_game_tracks":{"highest":{"GB2-01":58.702268945584024,"GB2-02":11.9006124570664,"GB2-03":24.333522158958257,"GB2-04":11.105048672649573,"GB2-05":47.672224676332476,"GB2-06":58.98721041188529,"GB2-07":41.98521707144406,"GB2-08":25.816619958052044},"medium":{"GB2-01":50.17608584714433,"GB2-02":11.519455639840443,"GB2-03":37.66702051583656,"GB2-04":9.440431376403948,"GB2-05":47.81965804820224,"GB2-06":48.32158623276131,"GB2-07":48.78610748121407,"GB2-08":63.79621550421799},"none":{"GB2-01":34.66903440809909,"GB2-02":14.666325543510737,"GB2-03":25.434893020124907,"GB2-04":27.00771287513746,"GB2-05":47.17007460611467,"GB2-06":40.911765857263845,"GB2-07":33.74687311206768,"GB2-08":65.9586238785346}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":35.062840543996515,"medium":39.69082008070261,"none":36.19566291260662},"reasoning_agg":{"highest":{"max":58.98721041188529,"mean":35.062840543996515,"min":11.105048672649573},"medium":{"max":63.79621550421799,"mean":39.69082008070261,"min":9.440431376403948},"none":{"max":65.9586238785346,"mean":36.19566291260662,"min":14.666325543510737}},"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":65.9586238785346,"expected_score":34.63599352683327,"reasoning_variance":4.627979536706093,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.3471143189353114},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":58.98721041188529,"expected_score":25.28984712590489,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.772993418091627},"medium":{"ceiling_score":63.79621550421799,"expected_score":39.29053195257066,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.4002881281319475},"none":{"ceiling_score":65.9586238785346,"expected_score":39.327601502024265,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.1319385894176435}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-flash:0eaf9e05a2b2ee2e","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.0376887,"median":0.037827133,"min":0.02582591,"recorded_attempt_count":11,"run_count":8,"total":0.3015096},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.006158996,"mean":0.00343607875,"median":0.002791493,"min":0.0021123,"recorded_attempt_count":11,"run_count":8,"total":0.027488630000000007}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.0376887,"median":0.037827133,"min":0.02582591,"recorded_attempt_count":11,"run_count":8,"total":0.3015096},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.006158996,"mean":0.00343607875,"median":0.002791493,"min":0.0021123,"recorded_attempt_count":11,"run_count":8,"total":0.027488629999999997}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":16,"cost_basis_counts":{"provider_reported":22},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.061982706,"mean":0.020562389374999997,"median":0.015992453,"min":0.0021123,"recorded_attempt_count":22,"run_count":16,"total":0.32899822999999995},"codegen_latency_ms":{"attempt_count":22,"max_ms":1377805,"mean_ms":526774.25,"min_ms":30630,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":11,"max_ms":1377805,"mean_ms":998592.5,"min_ms":680734,"run_count":8},"none":{"attempt_count":11,"max_ms":104368,"mean_ms":54956.0,"min_ms":30630,"run_count":8}},"codegen_output_tokens":{"attempt_count":22,"output_max":125053,"output_mean":40030.0625,"output_min":2070,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":11,"output_max":125053,"output_mean":76276.375,"output_min":52513,"run_count":8},"none":{"attempt_count":11,"output_max":7265,"output_mean":3783.75,"output_min":2070,"run_count":8}},"display_name":"Qwen3.8 Flash","economics":{"medium":47.131945224618256,"none":26.30110692557694},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":22,"finish_reasons":["stop"],"indexed_attempts":22,"output_token_observations":22,"provider_post_attempt_observations":22,"provider_post_attempts":22,"reasoning_token_observations":22,"reconciliation_get_attempt_observations":22,"reconciliation_get_attempts":100,"total_output_tokens":640481,"total_reasoning_output_tokens":544948,"total_visible_output_tokens":95533,"visible_token_observations":22},"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/qwen3.8-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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,"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":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":"qwen/qwen3.8-flash","is_recent_addition":false,"last_measured_at":"2026-09-26T05:47:07Z","match_totals_all":{"draws":1560,"losses":1562,"wins":1349},"match_totals_tracks":{"medium":{"draws":752,"losses":588,"wins":899},"none":{"draws":808,"losses":974,"wins":450}},"model_slug":"qwen-qwen3-8-flash","overall":{"max":73.0132641224563,"mean":36.7165260750976,"min":8.337863642679174},"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":34,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":208,"losses":232,"wins":162},"GB2-02":{"draws":391,"losses":76,"wins":61},"GB2-03":{"draws":137,"losses":165,"wins":191},"GB2-04":{"draws":346,"losses":102,"wins":60},"GB2-05":{"draws":0,"losses":286,"wins":222},"GB2-06":{"draws":47,"losses":192,"wins":373},"GB2-07":{"draws":0,"losses":325,"wins":231},"GB2-08":{"draws":431,"losses":184,"wins":49}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":124,"losses":120,"wins":92},"GB2-02":{"draws":160,"losses":45,"wins":57},"GB2-03":{"draws":50,"losses":64,"wins":125},"GB2-04":{"draws":157,"losses":53,"wins":38},"GB2-05":{"draws":0,"losses":84,"wins":164},"GB2-06":{"draws":37,"losses":52,"wins":183},"GB2-07":{"draws":0,"losses":78,"wins":202},"GB2-08":{"draws":224,"losses":92,"wins":38}},"none":{"GB2-01":{"draws":84,"losses":112,"wins":70},"GB2-02":{"draws":231,"losses":31,"wins":4},"GB2-03":{"draws":87,"losses":101,"wins":66},"GB2-04":{"draws":189,"losses":49,"wins":22},"GB2-05":{"draws":0,"losses":202,"wins":58},"GB2-06":{"draws":10,"losses":140,"wins":190},"GB2-07":{"draws":0,"losses":247,"wins":29},"GB2-08":{"draws":207,"losses":92,"wins":11}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1434.3789597511889,"GB2-02":1530.926875833122,"GB2-03":1541.5412060192216,"GB2-04":1562.4564651728103,"GB2-05":1739.5616631844578,"GB2-06":1871.2935624802321,"GB2-07":1838.4946857611073,"GB2-08":1396.8902635327127},"none":{"GB2-01":1388.0979068327533,"GB2-02":1411.2390211304682,"GB2-03":1436.056016364029,"GB2-04":1402.3000745538907,"GB2-05":1143.2555050672022,"GB2-06":1619.972010247095,"GB2-07":1038.9495636561776,"GB2-08":1312.9381736660907}},"per_game_tracks":{"medium":{"GB2-01":38.962512223157894,"GB2-02":25.080279785897684,"GB2-03":41.58465323981015,"GB2-04":35.520008265999564,"GB2-05":64.30226587688273,"GB2-06":73.0132641224563,"GB2-07":69.71458728692917,"GB2-08":28.87799099581258},"none":{"GB2-01":35.41997969078596,"GB2-02":8.337863642679174,"GB2-03":31.766741580293626,"GB2-04":11.044344304970318,"GB2-05":26.83512494843486,"GB2-06":57.99310512996687,"GB2-07":16.759011358726724,"GB2-08":22.252684748757982}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":47.131945224618256,"none":26.30110692557694},"reasoning_agg":{"medium":{"max":73.0132641224563,"mean":47.131945224618256,"min":25.080279785897684},"none":{"max":57.99310512996687,"mean":26.30110692557694,"min":8.337863642679174}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":73.0132641224563,"reasoning_variance":20.830838299041318},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":73.0132641224563,"expected_score":48.92802837530014,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7960831506818806},"none":{"ceiling_score":57.99310512996687,"expected_score":27.546027824292743,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.2449208987158045}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-terra:155aa79eccdb43f8","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.45800250000000003,"mean":0.38340421874999997,"median":0.38428625,"min":0.302056875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.0672337499999998},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.146648125,"mean":0.09696234375000001,"median":0.09060875000000002,"min":0.083821875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.7756987500000001},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.136415,"mean":0.07671781250000001,"median":0.0705246875,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6137425000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.146648125,"mean":0.09696234375000001,"median":0.09060875000000002,"min":0.083821875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.7756987500000001},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.136415,"mean":0.07671781250000001,"median":0.0705246875,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":0.6137425},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.45800250000000003,"mean":0.38340421874999997,"median":0.38428625,"min":0.302056875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":3.0672337499999998}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":28},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.45800250000000003,"mean":0.18569479166666666,"median":0.091314375,"min":0.058876874999999995,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":28},"run_count":24,"token_priced_attempt_count":28,"total":4.456675},"codegen_output_tokens":{"attempt_count":28,"output_max":28998,"output_mean":10500.666666666666,"output_min":2419,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":28998,"output_mean":23512.0,"output_min":18631,"run_count":8},"medium":{"attempt_count":9,"output_max":6917,"output_mean":4677.5,"output_min":3936,"run_count":8},"none":{"attempt_count":9,"output_max":6065,"output_mean":3312.5,"output_min":2419,"run_count":8}},"display_name":"GPT-5.6 Terra","economics":{"all":34.09070216010519,"highest":41.46519761948689,"medium":36.89069457476584,"none":28.388041130308466},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["stop"],"indexed_attempts":28,"output_token_observations":28,"provider_post_attempt_observations":28,"provider_post_attempts":28,"reasoning_token_observations":28,"reconciliation_get_attempt_observations":28,"total_output_tokens":252016,"total_reasoning_output_tokens":152800,"total_visible_output_tokens":99216,"visible_token_observations":28},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":["GB2-05"],"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":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-5.6-terra","is_recent_addition":false,"last_measured_at":"2026-09-26T06:47:23Z","match_totals_all":{"draws":2059,"losses":2371,"wins":2140},"match_totals_tracks":{"highest":{"draws":597,"losses":755,"wins":880},"medium":{"draws":629,"losses":879,"wins":796},"none":{"draws":833,"losses":737,"wins":464}},"model_slug":"gpt-5-6-terra","overall":{"max":75.52891428454922,"mean":35.270634374486285,"min":8.297684290657163},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":35,"overall_ranking_status":"ranked","per_game":{"GB2-01":61.729627009188654,"GB2-02":30.496188687689365,"GB2-03":30.01118426853946,"GB2-04":15.353188089113704,"GB2-05":51.39225759622981,"GB2-06":75.52891428454922,"GB2-07":40.19228961921556,"GB2-08":27.017931401369314},"per_game_all":{"GB2-01":57.04207878705464,"GB2-02":19.86820691538701,"GB2-03":23.954558508721664,"GB2-04":12.350360535396192,"GB2-06":52.6953351556352,"GB2-07":42.81542060911449,"GB2-08":29.908954609427145},"per_game_match_totals_all":{"GB2-01":{"draws":142,"losses":221,"wins":449},"GB2-02":{"draws":628,"losses":114,"wins":88},"GB2-03":{"draws":339,"losses":248,"wins":101},"GB2-04":{"draws":501,"losses":212,"wins":93},"GB2-05":{"draws":0,"losses":267,"wins":355},"GB2-06":{"draws":51,"losses":383,"wins":418},"GB2-07":{"draws":0,"losses":568,"wins":410},"GB2-08":{"draws":398,"losses":358,"wins":226}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":46,"losses":57,"wins":151},"GB2-02":{"draws":140,"losses":32,"wins":64},"GB2-03":{"draws":98,"losses":75,"wins":51},"GB2-04":{"draws":177,"losses":38,"wins":19},"GB2-05":{"draws":0,"losses":139,"wins":187},"GB2-06":{"draws":22,"losses":49,"wins":177},"GB2-07":{"draws":0,"losses":220,"wins":154},"GB2-08":{"draws":114,"losses":145,"wins":77}},"medium":{"GB2-01":{"draws":2,"losses":67,"wins":183},"GB2-02":{"draws":236,"losses":43,"wins":19},"GB2-03":{"draws":122,"losses":87,"wins":21},"GB2-04":{"draws":149,"losses":108,"wins":47},"GB2-05":{"draws":0,"losses":128,"wins":168},"GB2-06":{"draws":28,"losses":193,"wins":117},"GB2-07":{"draws":0,"losses":123,"wins":151},"GB2-08":{"draws":92,"losses":130,"wins":90}},"none":{"GB2-01":{"draws":94,"losses":97,"wins":115},"GB2-02":{"draws":252,"losses":39,"wins":5},"GB2-03":{"draws":119,"losses":86,"wins":29},"GB2-04":{"draws":175,"losses":66,"wins":27},"GB2-06":{"draws":1,"losses":141,"wins":124},"GB2-07":{"draws":0,"losses":225,"wins":105},"GB2-08":{"draws":192,"losses":83,"wins":59}}},"per_game_raw_elo_all":{"GB2-01":1686.8599001353386,"GB2-02":1493.1681701480418,"GB2-03":1354.0444292841635,"GB2-04":1410.516975544274,"GB2-06":1534.4168724784795,"GB2-07":1430.6650430645705,"GB2-08":1411.03456696042},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1752.3666211312961,"GB2-02":1570.9017626387488,"GB2-03":1418.9495760723196,"GB2-04":1431.7249225752669,"GB2-05":1531.0673934271622,"GB2-06":1914.0992692141342,"GB2-07":1389.4530681773392,"GB2-08":1373.4725606720285},"medium":{"GB2-01":1777.1085690164796,"GB2-02":1473.9979227746462,"GB2-03":1291.6732759699553,"GB2-04":1382.5380367672028,"GB2-05":1641.4549056389196,"GB2-06":1397.4045000243977,"GB2-07":1625.3836273106185,"GB2-08":1406.0612385326692},"none":{"GB2-01":1531.10451025824,"GB2-02":1434.6048250307308,"GB2-03":1351.5104358102158,"GB2-04":1417.2879672903516,"GB2-06":1291.7468481969058,"GB2-07":1277.1584337057536,"GB2-08":1453.5699016765616}},"per_game_tracks":{"highest":{"GB2-01":61.729627009188654,"GB2-02":30.496188687689365,"GB2-03":30.01118426853946,"GB2-04":15.353188089113704,"GB2-05":51.39225759622981,"GB2-06":75.52891428454922,"GB2-07":40.19228961921556,"GB2-08":27.017931401369314},"medium":{"GB2-01":63.51228677783417,"GB2-02":17.319170834556786,"GB2-03":18.11056241245301,"GB2-04":8.297684290657163,"GB2-05":58.26642250774223,"GB2-06":44.55133780034483,"GB2-07":55.585673702993965,"GB2-08":29.482418271544578},"none":{"GB2-01":45.8843225741411,"GB2-02":11.789261223914881,"GB2-03":23.74192884517252,"GB2-04":13.400209226417706,"GB2-06":38.00575338201153,"GB2-07":32.66829850513395,"GB2-08":33.22651415536755}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.46519761948689,"medium":36.89069457476584,"none":27.45601092920612},"reasoning_agg":{"highest":{"max":75.52891428454922,"mean":41.46519761948689,"min":15.353188089113704},"medium":{"max":63.51228677783417,"mean":36.89069457476584,"min":8.297684290657163},"none":{"max":45.8843225741411,"mean":27.45601092920612,"min":11.789261223914881}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":75.52891428454922,"expected_score":31.103259774259406,"reasoning_variance":14.009186690280767,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.167374600226879},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":75.52891428454922,"expected_score":33.34425188589341,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.12094573359348},"medium":{"ceiling_score":63.51228677783417,"expected_score":35.407094538705124,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.4836000360607144},"none":{"ceiling_score":45.8843225741411,"expected_score":30.37673307562999,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.92072214642387}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-8-27b:325c4507f070dddc","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3521656,"mean":0.19569013062499999,"median":0.187188825,"min":0.119031025,"recorded_attempt_count":11,"run_count":8,"total":1.5655210449999999},"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.079473456,"mean":0.042855077875,"median":0.0387132625,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.342840623},"none":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.045896320000000004,"mean":0.021958409999999998,"median":0.019045885,"min":0.011539076,"recorded_attempt_count":15,"run_count":8,"total":0.17566728000000004}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.079473456,"mean":0.042855077875,"median":0.0387132625,"min":0.0,"recorded_attempt_count":15,"run_count":8,"total":0.342840623},"historical-provider-setting-baseline":{"admitted_cell_count":3,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.045896320000000004,"mean":0.021958409999999998,"median":0.019045885,"min":0.011539076,"recorded_attempt_count":15,"run_count":8,"total":0.17566727999999998},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.3521656,"mean":0.19569013062499999,"median":0.187188825,"min":0.119031025,"recorded_attempt_count":11,"run_count":8,"total":1.5655210449999999}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":24,"cost_basis_counts":{"provider_reported":41},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.3521656,"mean":0.08683453949999999,"median":0.042413385,"min":0.0,"recorded_attempt_count":41,"run_count":24,"total":2.084028948},"codegen_latency_ms":{"attempt_count":41,"max_ms":2128037,"mean_ms":557159.5833333334,"min_ms":84532,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":2128037,"mean_ms":1259891.875,"min_ms":809012,"run_count":8},"medium":{"attempt_count":15,"max_ms":552808,"mean_ms":296150.0,"min_ms":144070,"run_count":8},"none":{"attempt_count":15,"max_ms":184099,"mean_ms":115436.875,"min_ms":84532,"run_count":8}},"codegen_output_tokens":{"attempt_count":40,"output_max":142524,"output_mean":34415.13043478261,"output_min":3853,"run_count":23},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":142524,"output_mean":77872.0,"output_min":45409,"run_count":8},"medium":{"attempt_count":14,"output_max":27551,"output_mean":16708.285714285714,"output_min":7740,"run_count":7},"none":{"attempt_count":15,"output_max":14298,"output_mean":6451.75,"output_min":3853,"run_count":8}},"display_name":"Qwen3.8 27B","economics":{"highest":51.343236475342515,"medium":42.32572697645675,"none":23.296694671118402},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":40,"finish_reasons":["stop"],"indexed_attempts":41,"output_token_observations":40,"provider_post_attempt_observations":41,"provider_post_attempts":41,"reasoning_token_observations":41,"reconciliation_get_attempt_observations":41,"reconciliation_get_attempts":199,"total_output_tokens":791548,"total_reasoning_output_tokens":610979,"total_visible_output_tokens":185807,"visible_token_observations":41},"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/qwen3.8-27b","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":7,"failed_game_aliases":["GB2-02","GB2-04"],"first_pass_admitted":2,"first_pass_rate":0.2857142857142857,"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":3,"repaired_rate":0.42857142857142855},"baseline":{"admitted_plugins":3,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03","GB2-05","GB2-06","GB2-07"],"first_pass_admitted":1,"first_pass_rate":0.125,"model_code_failure_rate":0.625,"model_code_failures":5,"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":2,"repaired_rate":0.25},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-03"],"first_pass_admitted":5,"first_pass_rate":0.625,"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":1,"repaired_rate":0.125}},"id":"qwen/qwen3.8-27b","is_recent_addition":false,"last_measured_at":"2026-09-26T05:33:08Z","match_totals_all":{"draws":859,"losses":1489,"wins":1595},"match_totals_tracks":{"highest":{"draws":220,"losses":626,"wins":914},"medium":{"draws":238,"losses":713,"wins":592},"none":{"draws":401,"losses":150,"wins":89}},"model_slug":"qwen-qwen3-8-27b","overall":{"max":74.7754111727451,"mean":34.97397213068939,"min":18.230648798221466},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","fixed_coverage_incomplete","generation_incomplete"],"overall_official_rank":36,"overall_ranking_status":"partial","per_game":{"GB2-01":57.751389865485,"GB2-04":54.00394478094825,"GB2-05":58.75534402179858,"GB2-06":32.90444740868511,"GB2-07":74.7754111727451,"GB2-08":29.868881602393042},"per_game_match_totals_all":{"GB2-01":{"draws":153,"losses":150,"wins":217},"GB2-03":{"draws":84,"losses":123,"wins":114},"GB2-04":{"draws":257,"losses":118,"wins":195},"GB2-05":{"draws":0,"losses":267,"wins":357},"GB2-06":{"draws":26,"losses":309,"wins":285},"GB2-07":{"draws":0,"losses":316,"wins":304},"GB2-08":{"draws":339,"losses":206,"wins":123}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":83,"wins":159},"GB2-04":{"draws":77,"losses":49,"wins":132},"GB2-05":{"draws":0,"losses":132,"wins":198},"GB2-06":{"draws":17,"losses":158,"wins":95},"GB2-07":{"draws":0,"losses":79,"wins":233},"GB2-08":{"draws":118,"losses":125,"wins":97}},"medium":{"GB2-01":{"draws":145,"losses":67,"wins":58},"GB2-03":{"draws":84,"losses":123,"wins":114},"GB2-05":{"draws":0,"losses":135,"wins":159},"GB2-06":{"draws":9,"losses":151,"wins":190},"GB2-07":{"draws":0,"losses":237,"wins":71}},"none":{"GB2-04":{"draws":180,"losses":69,"wins":63},"GB2-08":{"draws":221,"losses":81,"wins":26}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1697.5710645568845,"GB2-04":1682.4665788604555,"GB2-05":1648.0042487755254,"GB2-06":1207.0743600722512,"GB2-07":1913.6688351436223,"GB2-08":1410.0948627955906},"medium":{"GB2-01":1429.6059149220514,"GB2-03":1532.4162435286553,"GB2-05":1455.4965166139807,"GB2-06":1641.5711640079928,"GB2-07":1181.0188896765776},"none":{"GB2-04":1475.642015148466,"GB2-08":1334.439317034092}},"per_game_tracks":{"highest":{"GB2-01":57.751389865485,"GB2-04":54.00394478094825,"GB2-05":58.75534402179858,"GB2-06":32.90444740868511,"GB2-07":74.7754111727451,"GB2-08":29.868881602393042},"medium":{"GB2-01":38.43574497253667,"GB2-03":41.0599586033419,"GB2-05":46.56577078167427,"GB2-06":59.31595776161538,"GB2-07":26.251202763115543},"none":{"GB2-04":22.62392352124793,"GB2-08":23.969465820988876}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":47.78026534598191,"medium":38.9110022478648,"none":18.230648798221466},"reasoning_agg":{"highest":{"max":74.7754111727451,"mean":47.78026534598191,"min":29.868881602393042},"medium":{"max":59.31595776161538,"mean":38.9110022478648,"min":26.251202763115543},"none":{"max":23.969465820988876,"mean":18.230648798221466,"min":22.62392352124793}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":74.7754111727451,"reasoning_variance":29.549616547760444},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.7754111727451,"expected_score":43.33807453561306,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.442190810368849},"medium":{"ceiling_score":59.31595776161538,"expected_score":42.31184001556928,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.4008377677044805},"none":{"ceiling_score":23.969465820988876,"expected_score":23.773150327173788,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.542501528952322}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro:7bb1ed45eb8d62a0","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.913572594249},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.06923239834,"mean":0.046577516286750005,"median":0.0458058365,"min":0.023862969,"recorded_attempt_count":12,"run_count":8,"total":0.372620130294},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.20237245442100002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.06923239834,"mean":0.046577516286750005,"median":0.0458058365,"min":0.023862969,"recorded_attempt_count":12,"run_count":8,"total":0.37262013029400004},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.03845835,"mean":0.025296556802625002,"median":0.02540433020275,"min":0.014466934,"recorded_attempt_count":12,"run_count":8,"total":0.202372454421},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.176790095,"mean":0.114196574281125,"median":0.09418628700000001,"min":0.06074422244,"recorded_attempt_count":11,"run_count":8,"total":0.9135725942490001}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.176790095,"mean":0.062023549123500006,"median":0.0458058365,"min":0.014466934,"recorded_attempt_count":35,"run_count":24,"total":1.4885651789640002},"codegen_latency_ms":{"attempt_count":35,"max_ms":1560134,"mean_ms":432334.7916666667,"min_ms":52746,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":1560134,"mean_ms":818090.375,"min_ms":426935,"run_count":8},"medium":{"attempt_count":12,"max_ms":673313,"mean_ms":392142.875,"min_ms":86869,"run_count":8},"none":{"attempt_count":12,"max_ms":170011,"mean_ms":86771.125,"min_ms":52746,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":74570,"output_mean":21422.416666666668,"output_min":2493,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":74570,"output_mean":43080.25,"output_min":21434,"run_count":8},"medium":{"attempt_count":12,"output_max":23131,"output_mean":16655.5,"output_min":5286,"run_count":8},"none":{"attempt_count":12,"output_max":8274,"output_mean":4531.5,"output_min":2493,"run_count":8}},"display_name":"DeepSeek V4 Pro","economics":{"all":36.491756443568235,"highest":37.76647099819234,"medium":40.110131609801684,"none":28.739895761426514},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"reconciliation_get_attempts":166,"total_output_tokens":514138,"total_reasoning_output_tokens":410486,"total_visible_output_tokens":103652,"visible_token_observations":35},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":4,"first_pass_rate":0.5,"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":0.5},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","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},"intensive":{"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":"deepseek/deepseek-v4-pro","is_recent_addition":false,"last_measured_at":"2026-09-26T06:21:36Z","match_totals_all":{"draws":1781,"losses":2185,"wins":2146},"match_totals_tracks":{"highest":{"draws":725,"losses":785,"wins":718},"medium":{"draws":479,"losses":823,"wins":978},"none":{"draws":577,"losses":577,"wins":450}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":72.91420864056009,"mean":34.87402975122179,"min":7.881929306549962},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":37,"overall_ranking_status":"ranked","per_game":{"GB2-01":21.45524163229463,"GB2-02":10.933248546652026,"GB2-03":32.32936910769384,"GB2-04":24.96857237921988,"GB2-05":45.85469307850824,"GB2-06":71.69838955243416,"GB2-07":72.91420864056009,"GB2-08":21.978045048175847},"per_game_all":{"GB2-01":33.62502350544144,"GB2-03":23.67374496318342,"GB2-04":17.47717396257624,"GB2-05":47.506757096244606,"GB2-07":60.388745248072105,"GB2-08":36.27909388589159},"per_game_match_totals_all":{"GB2-01":{"draws":127,"losses":407,"wins":266},"GB2-02":{"draws":407,"losses":88,"wins":19},"GB2-03":{"draws":308,"losses":306,"wins":196},"GB2-04":{"draws":520,"losses":180,"wins":110},"GB2-05":{"draws":0,"losses":450,"wins":426},"GB2-06":{"draws":27,"losses":238,"wins":339},"GB2-07":{"draws":0,"losses":321,"wins":547},"GB2-08":{"draws":392,"losses":195,"wins":243}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":167,"wins":60},"GB2-02":{"draws":199,"losses":50,"wins":15},"GB2-03":{"draws":137,"losses":106,"wins":85},"GB2-04":{"draws":149,"losses":70,"wins":41},"GB2-05":{"draws":0,"losses":164,"wins":138},"GB2-06":{"draws":21,"losses":66,"wins":181},"GB2-07":{"draws":0,"losses":82,"wins":184},"GB2-08":{"draws":204,"losses":80,"wins":14}},"medium":{"GB2-01":{"draws":24,"losses":124,"wins":164},"GB2-02":{"draws":208,"losses":38,"wins":4},"GB2-03":{"draws":69,"losses":127,"wins":44},"GB2-04":{"draws":171,"losses":79,"wins":48},"GB2-05":{"draws":0,"losses":155,"wins":169},"GB2-06":{"draws":6,"losses":172,"wins":158},"GB2-07":{"draws":0,"losses":84,"wins":170},"GB2-08":{"draws":1,"losses":44,"wins":221}},"none":{"GB2-01":{"draws":88,"losses":116,"wins":42},"GB2-03":{"draws":102,"losses":73,"wins":67},"GB2-04":{"draws":200,"losses":31,"wins":21},"GB2-05":{"draws":0,"losses":131,"wins":119},"GB2-07":{"draws":0,"losses":155,"wins":193},"GB2-08":{"draws":187,"losses":71,"wins":8}}},"per_game_raw_elo_all":{"GB2-01":1363.3787659100533,"GB2-03":1349.1830853786862,"GB2-04":1443.825513388507,"GB2-05":1470.6407508608324,"GB2-07":1697.4437395121697,"GB2-08":1495.0957707730824},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1196.232547805928,"GB2-02":1429.856310985429,"GB2-03":1439.0605390044886,"GB2-04":1493.0777754649525,"GB2-05":1443.8810886057918,"GB2-06":1849.6950817687766,"GB2-07":1887.431863882211,"GB2-08":1309.8485796547113},"medium":{"GB2-01":1580.5672756011322,"GB2-02":1408.7528707417707,"GB2-03":1244.270032210312,"GB2-04":1419.702586792784,"GB2-05":1591.712689334062,"GB2-06":1456.029012412118,"GB2-07":1781.901849997087,"GB2-08":1887.1990506126856},"none":{"GB2-01":1313.3364743230995,"GB2-03":1364.2186849212585,"GB2-04":1418.6961779077844,"GB2-05":1376.328474642643,"GB2-07":1422.9975046572113,"GB2-08":1288.2396820518502}},"per_game_tracks":{"highest":{"GB2-01":21.45524163229463,"GB2-02":10.933248546652026,"GB2-03":32.32936910769384,"GB2-04":24.96857237921988,"GB2-05":45.85469307850824,"GB2-06":71.69838955243416,"GB2-07":72.91420864056009,"GB2-08":21.978045048175847},"medium":{"GB2-01":49.47831471809495,"GB2-02":7.881929306549962,"GB2-03":13.717815379784653,"GB2-04":13.963213350003095,"GB2-05":55.20222329139329,"GB2-06":48.08701204264685,"GB2-07":65.88852907145586,"GB2-08":66.6620157184848},"none":{"GB2-01":29.941514165934752,"GB2-03":24.97405040207176,"GB2-04":13.499736158505744,"GB2-05":41.463354918832295,"GB2-07":42.36349803220037,"GB2-08":20.197220891014144}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.76647099819234,"medium":40.110131609801684,"none":26.74548664567135},"reasoning_agg":{"highest":{"max":72.91420864056009,"mean":37.76647099819234,"min":10.933248546652026},"medium":{"max":66.6620157184848,"mean":40.110131609801684,"min":7.881929306549962},"none":{"max":42.36349803220037,"mean":26.74548664567135,"min":13.499736158505744}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":72.91420864056009,"expected_score":33.728094956813685,"reasoning_variance":13.364644964130335,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.145934794408106},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.91420864056009,"expected_score":28.681563826310416,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.084907171881923},"medium":{"ceiling_score":66.6620157184848,"expected_score":38.9267607007299,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.1833709090717832},"none":{"ceiling_score":42.36349803220037,"expected_score":29.31749360441455,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.572006958743202}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-pro-0813:e0f8ea8c59cf3cd4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28337826924,"mean":0.14657020603499998,"median":0.140081106,"min":0.07036986,"recorded_attempt_count":10,"run_count":8,"total":1.17256164828},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.18085216,"mean":0.12355654023,"median":0.14129957716,"min":0.04648314,"recorded_attempt_count":9,"run_count":8,"total":0.9884523218400001},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0508167,"mean":0.02704530848,"median":0.020221080000000002,"min":0.01808105112,"recorded_attempt_count":12,"run_count":8,"total":0.21636246784000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.18085216,"mean":0.12355654023,"median":0.14129957716,"min":0.04648314,"recorded_attempt_count":9,"run_count":8,"total":0.9884523218400001},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0508167,"mean":0.02704530848,"median":0.020221080000000002,"min":0.01808105112,"recorded_attempt_count":12,"run_count":8,"total":0.21636246784},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.28337826924,"mean":0.14657020603499998,"median":0.140081106,"min":0.07036986,"recorded_attempt_count":10,"run_count":8,"total":1.17256164828}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":31},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.28337826924,"mean":0.09905735158166666,"median":0.10177922040000001,"min":0.01808105112,"recorded_attempt_count":31,"run_count":24,"total":2.37737643796},"codegen_latency_ms":{"attempt_count":31,"max_ms":1461124,"mean_ms":482100.7083333333,"min_ms":19301,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":10,"max_ms":1461124,"mean_ms":902169.625,"min_ms":499972,"run_count":8},"medium":{"attempt_count":9,"max_ms":676490,"mean_ms":489467.75,"min_ms":326732,"run_count":8},"none":{"attempt_count":12,"max_ms":131002,"mean_ms":54664.75,"min_ms":19301,"run_count":8}},"codegen_output_tokens":{"attempt_count":31,"output_max":106197,"output_mean":33246.666666666664,"output_min":2345,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":10,"output_max":106197,"output_mean":60744.125,"output_min":32963,"run_count":8},"medium":{"attempt_count":9,"output_max":42157,"output_mean":35085.125,"output_min":20989,"run_count":8},"none":{"attempt_count":12,"output_max":10866,"output_mean":3910.75,"output_min":2345,"run_count":8}},"display_name":"DeepSeek V4 Pro 0813","economics":{"all":36.39399963480636,"highest":41.295875199535175,"medium":34.03605377798529,"none":31.4732446025812},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":31,"finish_reasons":["stop"],"indexed_attempts":31,"output_token_observations":31,"provider_post_attempt_observations":31,"provider_post_attempts":31,"reasoning_token_observations":31,"reconciliation_get_attempt_observations":31,"reconciliation_get_attempts":150,"total_output_tokens":797920,"total_reasoning_output_tokens":686933,"total_visible_output_tokens":110987,"visible_token_observations":31},"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-0813","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.625,"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":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":"deepseek/deepseek-v4-pro-0813","is_recent_addition":false,"last_measured_at":"2026-09-26T03:01:17Z","match_totals_all":{"draws":1899,"losses":2210,"wins":2043},"match_totals_tracks":{"highest":{"draws":635,"losses":673,"wins":930},"medium":{"draws":669,"losses":896,"wins":789},"none":{"draws":595,"losses":641,"wins":324}},"model_slug":"deepseek-deepseek-v4-pro-0813","overall":{"max":72.33131596883865,"mean":34.87369444546382,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":38,"overall_ranking_status":"ranked","per_game":{"GB2-01":39.03640268350778,"GB2-02":12.753629707247093,"GB2-03":48.1843846315724,"GB2-04":13.574500593198664,"GB2-05":67.56817063638168,"GB2-06":60.544268151701395,"GB2-07":72.33131596883865,"GB2-08":16.374329223833715},"per_game_all":{"GB2-01":37.77306385811567,"GB2-03":35.53465436185616,"GB2-04":12.203451909906098,"GB2-06":53.68663061142976,"GB2-07":55.47070030209394,"GB2-08":23.695496765436573},"per_game_match_totals_all":{"GB2-01":{"draws":278,"losses":308,"wins":264},"GB2-02":{"draws":412,"losses":105,"wins":17},"GB2-03":{"draws":198,"losses":325,"wins":283},"GB2-04":{"draws":461,"losses":268,"wins":117},"GB2-05":{"draws":0,"losses":180,"wins":342},"GB2-06":{"draws":37,"losses":429,"wins":422},"GB2-07":{"draws":0,"losses":330,"wins":486},"GB2-08":{"draws":513,"losses":265,"wins":112}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":11,"losses":110,"wins":133},"GB2-02":{"draws":232,"losses":41,"wins":9},"GB2-03":{"draws":27,"losses":85,"wins":136},"GB2-04":{"draws":167,"losses":99,"wins":56},"GB2-05":{"draws":0,"losses":64,"wins":190},"GB2-06":{"draws":13,"losses":108,"wins":197},"GB2-07":{"draws":0,"losses":59,"wins":207},"GB2-08":{"draws":185,"losses":107,"wins":2}},"medium":{"GB2-01":{"draws":204,"losses":72,"wins":70},"GB2-02":{"draws":180,"losses":64,"wins":8},"GB2-03":{"draws":48,"losses":162,"wins":108},"GB2-04":{"draws":95,"losses":106,"wins":41},"GB2-05":{"draws":0,"losses":116,"wins":152},"GB2-06":{"draws":21,"losses":181,"wins":110},"GB2-07":{"draws":0,"losses":81,"wins":203},"GB2-08":{"draws":121,"losses":114,"wins":97}},"none":{"GB2-01":{"draws":63,"losses":126,"wins":61},"GB2-03":{"draws":123,"losses":78,"wins":39},"GB2-04":{"draws":199,"losses":63,"wins":20},"GB2-06":{"draws":3,"losses":140,"wins":115},"GB2-07":{"draws":0,"losses":190,"wins":76},"GB2-08":{"draws":207,"losses":44,"wins":13}}},"per_game_raw_elo_all":{"GB2-01":1420.0701640429413,"GB2-03":1475.697876208999,"GB2-04":1408.9954360283427,"GB2-06":1550.2707665744135,"GB2-07":1623.7441512131372,"GB2-08":1332.115166005469},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1438.6599900316537,"GB2-02":1442.0553790303168,"GB2-03":1611.460619978248,"GB2-04":1416.2924084625038,"GB2-05":1791.1885938892274,"GB2-06":1662.9605213954346,"GB2-07":1878.6292203429311,"GB2-08":1237.7695892664476},"medium":{"GB2-01":1493.0020389806919,"GB2-02":1421.1096020804257,"GB2-03":1393.426400325395,"GB2-04":1331.1981397127938,"GB2-05":1454.8185414839636,"GB2-06":1374.0057009749626,"GB2-07":1846.2932577520542,"GB2-08":1433.1234768017516},"none":{"GB2-01":1328.548463116478,"GB2-03":1422.206608323354,"GB2-04":1479.4957599097306,"GB2-06":1613.8460773528427,"GB2-07":1146.3099755444266,"GB2-08":1325.4524319482082}},"per_game_tracks":{"highest":{"GB2-01":39.03640268350778,"GB2-02":12.753629707247093,"GB2-03":48.1843846315724,"GB2-04":13.574500593198664,"GB2-05":67.56817063638168,"GB2-06":60.544268151701395,"GB2-07":72.33131596883865,"GB2-08":16.374329223833715},"medium":{"GB2-01":43.22612538921468,"GB2-02":9.627129721536212,"GB2-03":28.01859709783625,"GB2-04":0.0,"GB2-05":46.45397594397124,"GB2-06":43.08520073232897,"GB2-07":70.24211998290876,"GB2-08":31.635281356086193},"none":{"GB2-01":31.056663501624545,"GB2-03":30.40098135615985,"GB2-04":23.035855136519633,"GB2-06":57.43042295025894,"GB2-07":23.8386649545344,"GB2-08":23.076879716389808}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.295875199535175,"medium":34.03605377798529,"none":29.28915435887099},"reasoning_agg":{"highest":{"max":72.33131596883865,"mean":41.295875199535175,"min":12.753629707247093},"medium":{"max":70.24211998290876,"mean":34.03605377798529,"min":0.0},"none":{"max":57.43042295025894,"mean":29.28915435887099,"min":23.035855136519633}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":72.33131596883865,"expected_score":33.31610842453629,"reasoning_variance":12.006720840664183,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.5575860209275305},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":72.33131596883865,"expected_score":32.810745358696394,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.48512984083878},"medium":{"ceiling_score":70.24211998290876,"expected_score":32.591200591005304,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.4448531869799837},"none":{"ceiling_score":57.43042295025894,"expected_score":33.46101320642105,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.171858847550059}}},{"canonical_public_row_identity":"publication-row.v1:overall:z-ai-glm-5-2:50fed1035ee7c556","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303000003},"medium":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":26},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.14635563000000001,"mean":0.0939111476625,"median":0.10304704349999999,"min":0.032703412,"recorded_attempt_count":26,"run_count":16,"total":1.5025783626},"none":{"admitted_cell_count":24,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.03729904666666666,"mean":0.023546225995833333,"median":0.024102434966666666,"min":0.013816857666666666,"recorded_attempt_count":37,"run_count":24,"total":0.5651094239}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.23894740000000003,"mean":0.121926546075,"median":0.109979,"min":0.0289264146,"recorded_attempt_count":10,"run_count":8,"total":0.9754123686},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"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},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":16,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.047757869999999994,"mean":0.022448211274999998,"median":0.017169796,"min":0.0106770175,"recorded_attempt_count":24,"run_count":16,"total":0.3591713804},"historical-provider-setting-baseline-variant-2":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.050486600000000006,"mean":0.0257422554375,"median":0.02408436405,"min":0.0093287,"recorded_attempt_count":13,"run_count":8,"total":0.2059380435},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.1808710912875,"median":0.13158330000000001,"min":0.0448038366,"recorded_attempt_count":9,"run_count":8,"total":1.4469687303}},"codegen_cost_usd":{"admitted_cell_count":48,"cell_count":24,"cost_basis_counts":{"provider_reported":72},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.39278997800000004,"mean":0.09944282164861112,"median":0.056673037849999996,"min":0.013816857666666666,"recorded_attempt_count":72,"run_count":48,"total":3.5146565167999997},"codegen_latency_ms":{"attempt_count":32,"max_ms":882507,"mean_ms":240683.0,"min_ms":16088,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":882507,"mean_ms":333475.125,"min_ms":88401,"run_count":8},"medium":{"attempt_count":10,"max_ms":677392,"mean_ms":353638.875,"min_ms":112475,"run_count":8},"none":{"attempt_count":13,"max_ms":79329,"mean_ms":34935.0,"min_ms":16088,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":130069,"output_mean":34536.041666666664,"output_min":1442,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":130069,"output_mean":52728.5,"output_min":20107,"run_count":8},"medium":{"attempt_count":10,"output_max":83540,"output_mean":46751.875,"output_min":17329,"run_count":8},"none":{"attempt_count":13,"output_max":8574,"output_mean":4127.75,"output_min":1442,"run_count":8}},"display_name":"GLM-5.2","economics":{"all":33.68855546912035,"highest":33.39344149417892,"medium":37.49945825507596,"none":30.17276665810619},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":32,"finish_reasons":["stop"],"indexed_attempts":32,"output_token_observations":32,"provider_post_attempt_observations":32,"provider_post_attempts":32,"reasoning_token_observations":32,"reconciliation_get_attempt_observations":32,"reconciliation_get_attempts":148,"total_output_tokens":828865,"total_reasoning_output_tokens":728689,"total_visible_output_tokens":100176,"visible_token_observations":32},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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":"z-ai/glm-5.2","is_recent_addition":false,"last_measured_at":"2026-09-26T06:01:13Z","match_totals_all":{"draws":3788,"losses":4030,"wins":3298},"match_totals_tracks":{"highest":{"draws":669,"losses":853,"wins":592},"medium":{"draws":1338,"losses":1171,"wins":1213},"none":{"draws":1781,"losses":2006,"wins":1493}},"model_slug":"z-ai-glm-5-2","overall":{"max":74.83136926483846,"mean":33.68855546912036,"min":8.095434796717493},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":39,"overall_ranking_status":"ranked","per_game":{"GB2-01":46.404498088563045,"GB2-02":32.543444872865365,"GB2-03":30.096215584262822,"GB2-04":31.06007188530032,"GB2-05":54.68992885024498,"GB2-06":44.4754295158053,"GB2-07":8.095434796717493,"GB2-08":19.78250835967206},"per_game_all":{"GB2-01":34.38864207521309,"GB2-02":19.566120419651835,"GB2-03":26.312926163371156,"GB2-04":23.698609115256318,"GB2-05":47.89714236465562,"GB2-06":55.5332541180292,"GB2-07":37.812864199300925,"GB2-08":24.29888529748472},"per_game_match_totals_all":{"GB2-01":{"draws":435,"losses":554,"wins":363},"GB2-02":{"draws":1080,"losses":165,"wins":131},"GB2-03":{"draws":521,"losses":409,"wins":180},"GB2-04":{"draws":771,"losses":337,"wins":236},"GB2-05":{"draws":0,"losses":760,"wins":608},"GB2-06":{"draws":95,"losses":489,"wins":818},"GB2-07":{"draws":0,"losses":858,"wins":736},"GB2-08":{"draws":886,"losses":458,"wins":226}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":113,"losses":92,"wins":119},"GB2-02":{"draws":125,"losses":34,"wins":79},"GB2-03":{"draws":119,"losses":70,"wins":47},"GB2-04":{"draws":88,"losses":90,"wins":72},"GB2-05":{"draws":0,"losses":132,"wins":112},"GB2-06":{"draws":13,"losses":118,"wins":135},"GB2-07":{"draws":0,"losses":240,"wins":26},"GB2-08":{"draws":211,"losses":77,"wins":2}},"medium":{"GB2-01":{"draws":171,"losses":138,"wins":119},"GB2-02":{"draws":357,"losses":62,"wins":47},"GB2-03":{"draws":197,"losses":148,"wins":19},"GB2-04":{"draws":265,"losses":108,"wins":77},"GB2-05":{"draws":0,"losses":234,"wins":264},"GB2-06":{"draws":24,"losses":98,"wins":366},"GB2-07":{"draws":0,"losses":214,"wins":314},"GB2-08":{"draws":324,"losses":169,"wins":7}},"none":{"GB2-01":{"draws":151,"losses":324,"wins":125},"GB2-02":{"draws":598,"losses":69,"wins":5},"GB2-03":{"draws":205,"losses":191,"wins":114},"GB2-04":{"draws":418,"losses":139,"wins":87},"GB2-05":{"draws":0,"losses":394,"wins":232},"GB2-06":{"draws":58,"losses":273,"wins":317},"GB2-07":{"draws":0,"losses":404,"wins":396},"GB2-08":{"draws":351,"losses":212,"wins":217}}},"per_game_raw_elo_all":{"GB2-01":1375.2072864893833,"GB2-02":1493.09643548225,"GB2-03":1381.6456600119416,"GB2-04":1486.3370759778165,"GB2-05":1479.7415277258824,"GB2-06":1583.1863013553236,"GB2-07":1357.2350638554606,"GB2-08":1341.0125342975846},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1537.6541154025683,"GB2-02":1585.405527054358,"GB2-03":1419.1726145686785,"GB2-04":1533.279133719637,"GB2-05":1586.934412523432,"GB2-06":1398.9018421194878,"GB2-07":908.561158379106,"GB2-08":1281.8625989732889},"medium":{"GB2-01":1366.0836904773305,"GB2-02":1476.6298478888903,"GB2-03":1327.0654092484756,"GB2-04":1477.8950970252781,"GB2-05":1560.6889174367866,"GB2-06":1902.829895655052,"GB2-07":1678.7686816854145,"GB2-08":1271.1087759176776},"none":{"GB2-01":1221.8840535882507,"GB2-02":1417.2539315035017,"GB2-03":1398.6989562186707,"GB2-04":1447.8369971885354,"GB2-05":1291.6012532174286,"GB2-06":1447.8271662914306,"GB2-07":1484.3753515018611,"GB2-08":1470.0662280017875}},"per_game_tracks":{"highest":{"GB2-01":46.404498088563045,"GB2-02":32.543444872865365,"GB2-03":30.096215584262822,"GB2-04":31.06007188530032,"GB2-05":54.68992885024498,"GB2-06":44.4754295158053,"GB2-07":8.095434796717493,"GB2-08":19.78250835967206},"medium":{"GB2-01":33.61222310832579,"GB2-02":17.26530551001238,"GB2-03":21.048775171302836,"GB2-04":22.345359261657478,"GB2-05":53.00111467495336,"GB2-06":74.83136926483846,"GB2-07":59.08582825423472,"GB2-08":18.805690795282683},"none":{"GB2-01":23.14920502875045,"GB2-02":8.889610876077759,"GB2-03":27.7937877345478,"GB2-04":17.690396198811165,"GB2-05":36.00038356876851,"GB2-06":47.29296357344385,"GB2-07":46.257329546950565,"GB2-08":34.30845673749941}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":33.39344149417892,"medium":37.49945825507596,"none":30.172766658106195},"reasoning_agg":{"highest":{"max":54.68992885024498,"mean":33.39344149417892,"min":8.095434796717493},"medium":{"max":74.83136926483846,"mean":37.49945825507596,"min":17.26530551001238},"none":{"max":47.29296357344385,"mean":30.172766658106195,"min":8.889610876077759}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":74.83136926483846,"expected_score":30.98515941581905,"reasoning_variance":7.326691596969763,"reliability_score":99.99356431801245,"uncertainty_avg":0.006435681987559301,"uncertainty_penalty":-2.703396053301308},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.68992885024498,"expected_score":23.689456293282046,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.703985200896877},"medium":{"ceiling_score":74.83136926483846,"expected_score":37.595885677983574,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.09642742290761674},"none":{"ceiling_score":47.29296357344385,"expected_score":31.670136276191535,"reliability_score":99.98069295403732,"uncertainty_avg":0.019307045962677905,"uncertainty_penalty":1.4973696180853402}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5-pro:1173fd470ce74d1d","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"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},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.0317000854,"median":0.0104556789,"min":0.0057139812,"recorded_attempt_count":11,"run_count":8,"total":0.2536006832}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.2996388,"mean":0.13471628689999998,"median":0.1144847257,"min":0.027613287599999998,"recorded_attempt_count":17,"run_count":8,"total":1.0777302951999999},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.1311545862,"mean":0.0317000854,"median":0.0104556789,"min":0.0057139812,"recorded_attempt_count":11,"run_count":8,"total":0.2536006832}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":16,"cost_basis_counts":{"provider_reported":28},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.2996388,"mean":0.08320818615,"median":0.048126608099999996,"min":0.0057139812,"recorded_attempt_count":28,"run_count":16,"total":1.3313309784},"codegen_latency_ms":{"attempt_count":28,"max_ms":2144825,"mean_ms":691475.625,"min_ms":43161,"run_count":16},"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":11,"max_ms":886851,"mean_ms":223216.625,"min_ms":43161,"run_count":8}},"codegen_output_tokens":{"attempt_count":28,"output_max":131072,"output_mean":41065.3125,"output_min":2846,"run_count":16},"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":11,"output_max":42691,"output_mean":10871.125,"output_min":2846,"run_count":8}},"display_name":"MiMo-V2.5-Pro","economics":{"medium":42.52079587165148,"none":27.954084067301828},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":28,"finish_reasons":["error","length","stop"],"indexed_attempts":28,"output_token_observations":28,"total_output_tokens":657045},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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":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}},"id":"xiaomi/mimo-v2.5-pro","is_recent_addition":false,"last_measured_at":"2026-09-26T07:10:17Z","match_totals_all":{"draws":815,"losses":1306,"wins":1127},"match_totals_tracks":{"medium":{"draws":329,"losses":649,"wins":682},"none":{"draws":486,"losses":657,"wins":445}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":66.96196231894882,"mean":33.303180352175204,"min":3.0276416700616027},"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":114,"losses":247,"wins":313},"GB2-02":{"draws":182,"losses":37,"wins":13},"GB2-03":{"draws":82,"losses":56,"wins":30},"GB2-04":{"draws":124,"losses":44,"wins":56},"GB2-05":{"draws":0,"losses":288,"wins":148},"GB2-06":{"draws":8,"losses":193,"wins":281},"GB2-07":{"draws":0,"losses":286,"wins":278},"GB2-08":{"draws":305,"losses":155,"wins":8}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":43,"losses":121,"wins":236},"GB2-04":{"draws":124,"losses":44,"wins":56},"GB2-05":{"draws":0,"losses":145,"wins":75},"GB2-06":{"draws":3,"losses":69,"wins":182},"GB2-07":{"draws":0,"losses":175,"wins":131},"GB2-08":{"draws":159,"losses":95,"wins":2}},"none":{"GB2-01":{"draws":71,"losses":126,"wins":77},"GB2-02":{"draws":182,"losses":37,"wins":13},"GB2-03":{"draws":82,"losses":56,"wins":30},"GB2-05":{"draws":0,"losses":143,"wins":73},"GB2-06":{"draws":5,"losses":124,"wins":99},"GB2-07":{"draws":0,"losses":111,"wins":147},"GB2-08":{"draws":146,"losses":60,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1787.2591725363961,"GB2-04":1509.2613046073357,"GB2-05":1287.7221620012729,"GB2-06":1771.907827304494,"GB2-07":1429.791922284171,"GB2-08":1258.814719154205},"none":{"GB2-01":1370.9700650030159,"GB2-02":1375.0615005659079,"GB2-03":1315.1846312921423,"GB2-05":1138.4250381896366,"GB2-06":1343.1142662669545,"GB2-07":1543.3981980059082,"GB2-08":1302.3960593741}},"per_game_tracks":{"medium":{"GB2-01":64.62076197928616,"GB2-04":27.158379262739263,"GB2-05":35.786178117567985,"GB2-06":66.96196231894882,"GB2-07":42.71953326200743,"GB2-08":17.877960289359237},"none":{"GB2-01":34.206916352088754,"GB2-02":3.0276416700616027,"GB2-03":19.89762811578062,"GB2-05":26.38072300618391,"GB2-06":40.98922950084422,"GB2-07":50.10817358838301,"GB2-08":21.068276237770675}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.57005925104736,"none":27.036301453303054},"reasoning_agg":{"medium":{"max":66.96196231894882,"mean":39.57005925104736,"min":17.877960289359237},"none":{"max":50.10817358838301,"mean":27.036301453303054,"min":3.0276416700616027}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":66.96196231894882,"reasoning_variance":12.533757797744308},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":66.96196231894882,"expected_score":44.10730320535753,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.537243954310171},"none":{"ceiling_score":50.10817358838301,"expected_score":28.320768920545085,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.284467467242031}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5:afe5edea083200ed","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"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},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.21477374999999999,"mean":0.17756265624999998,"median":0.17285124999999998,"min":0.1418975,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":1.42050125},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":12},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":4.45591875},"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":{"all":36.810447597041474,"highest":37.632813462408045,"medium":33.98898760273479,"none":30.880726440569067},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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},"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":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":0.25},"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":"2026-09-26T03:49:30Z","match_totals_all":{"draws":1257,"losses":1431,"wins":1332},"match_totals_tracks":{"highest":{"draws":549,"losses":531,"wins":570},"medium":{"draws":420,"losses":558,"wins":526},"none":{"draws":288,"losses":342,"wins":236}},"model_slug":"gpt-5","overall":{"max":70.24762372804868,"mean":33.0812119482008,"min":0.7018851972411863},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings","fixed_coverage_incomplete"],"overall_official_rank":41,"overall_ranking_status":"partial","per_game":{"GB2-01":30.659305102959554,"GB2-02":9.57562445696167,"GB2-03":21.166022861640844,"GB2-04":18.002204397829445,"GB2-05":69.85287882563414,"GB2-06":70.24762372804868,"GB2-07":58.77373137074688,"GB2-08":22.785116955443208},"per_game_all":{"GB2-01":34.45280411161019,"GB2-03":13.187837744453008,"GB2-05":58.513612875956994,"GB2-07":53.82178394894081,"GB2-08":24.07619930424637},"per_game_match_totals_all":{"GB2-01":{"draws":61,"losses":283,"wins":176},"GB2-02":{"draws":292,"losses":62,"wins":14},"GB2-03":{"draws":138,"losses":191,"wins":51},"GB2-04":{"draws":304,"losses":93,"wins":55},"GB2-05":{"draws":0,"losses":186,"wins":304},"GB2-06":{"draws":26,"losses":149,"wins":261},"GB2-07":{"draws":0,"losses":259,"wins":407},"GB2-08":{"draws":436,"losses":208,"wins":64}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":105,"wins":78},"GB2-02":{"draws":165,"losses":30,"wins":13},"GB2-03":{"draws":57,"losses":63,"wins":26},"GB2-04":{"draws":149,"losses":46,"wins":17},"GB2-05":{"draws":0,"losses":56,"wins":118},"GB2-06":{"draws":10,"losses":50,"wins":140},"GB2-07":{"draws":0,"losses":93,"wins":145},"GB2-08":{"draws":147,"losses":88,"wins":33}},"medium":{"GB2-01":{"draws":27,"losses":138,"wins":33},"GB2-03":{"draws":60,"losses":57,"wins":19},"GB2-04":{"draws":155,"losses":47,"wins":38},"GB2-05":{"draws":0,"losses":64,"wins":128},"GB2-06":{"draws":16,"losses":99,"wins":121},"GB2-07":{"draws":0,"losses":77,"wins":173},"GB2-08":{"draws":162,"losses":76,"wins":14}},"none":{"GB2-01":{"draws":13,"losses":40,"wins":65},"GB2-02":{"draws":127,"losses":32,"wins":1},"GB2-03":{"draws":21,"losses":71,"wins":6},"GB2-05":{"draws":0,"losses":66,"wins":58},"GB2-07":{"draws":0,"losses":89,"wins":89},"GB2-08":{"draws":127,"losses":44,"wins":17}}},"per_game_raw_elo_all":{"GB2-01":1381.2350610149058,"GB2-03":1248.6403062166403,"GB2-05":1653.7770978001724,"GB2-07":1601.6314096827625,"GB2-08":1339.9731070266314},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1325.7448951498568,"GB2-02":1423.2627667948634,"GB2-03":1330.9350811768652,"GB2-04":1450.3093617876625,"GB2-05":1832.7029710975191,"GB2-06":1829.491946583697,"GB2-07":1675.2815131711031,"GB2-08":1321.5080588770336},"medium":{"GB2-01":1084.7776683347013,"GB2-03":1295.1037316124425,"GB2-04":1422.0999256997284,"GB2-05":1674.5383011770475,"GB2-06":1506.0176888586416,"GB2-07":1694.9908914340676,"GB2-08":1313.8771779827632},"none":{"GB2-01":1733.1826195601586,"GB2-02":1426.6406709795294,"GB2-03":1119.8821058606138,"GB2-05":1454.0900211259502,"GB2-07":1434.6218244431168,"GB2-08":1384.5340842200976}},"per_game_tracks":{"highest":{"GB2-01":30.659305102959554,"GB2-02":9.57562445696167,"GB2-03":21.166022861640844,"GB2-04":18.002204397829445,"GB2-05":69.85287882563414,"GB2-06":70.24762372804868,"GB2-07":58.77373137074688,"GB2-08":22.785116955443208},"medium":{"GB2-01":13.19773628892919,"GB2-03":17.69560517447699,"GB2-04":13.926963290137088,"GB2-05":59.99608453661076,"GB2-06":50.85198428028828,"GB2-07":60.120302482830986,"GB2-08":22.134237165870218},"none":{"GB2-01":59.50137094294183,"GB2-02":9.508665452935052,"GB2-03":0.7018851972411863,"GB2-05":45.69187526562608,"GB2-07":42.57131799324459,"GB2-08":27.309243791425686}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":37.632813462408045,"medium":32.8730683039981,"none":28.737754078196257},"reasoning_agg":{"highest":{"max":70.24762372804868,"mean":37.632813462408045,"min":9.57562445696167},"medium":{"max":60.120302482830986,"mean":32.8730683039981,"min":13.19773628892919},"none":{"max":59.50137094294183,"mean":28.737754078196257,"min":0.7018851972411863}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":70.24762372804868,"expected_score":34.61986211892504,"reasoning_variance":8.895059384211788,"reliability_score":99.36278832237554,"uncertainty_avg":0.6372116776244644,"uncertainty_penalty":1.5386501707242388},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":70.24762372804868,"expected_score":29.098521979803834,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.53429148260421},"medium":{"ceiling_score":60.120302482830986,"expected_score":33.46945186141216,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.5963835574140575},"none":{"ceiling_score":59.50137094294183,"expected_score":33.96894848691837,"reliability_score":98.40697080593884,"uncertainty_avg":1.5930291940611607,"uncertainty_penalty":5.231194408722114}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-6-luna:cefd28a14bc6fb2f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.0117399875,"median":0.011861425,"min":0.0087063,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.09391989999999999},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0044690500000000005,"mean":0.0038361124999999998,"median":0.0037657374999999996,"min":0.00283105,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.030688899999999998},"none":{"admitted_cell_count":7,"cell_count":7,"cost_basis_counts":{"local_standard_estimate":7},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.0030818,"mean":0.0023309607142857143,"median":0.0023213,"min":0.00161355,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":7},"run_count":7,"token_priced_attempt_count":7,"total":0.016316725}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.0044690500000000005,"mean":0.0038361124999999998,"median":0.0037657374999999996,"min":0.00283105,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0306889},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":7,"cost_basis_counts":{"local_standard_estimate":7},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.0030818,"mean":0.0023309607142857143,"median":0.0023213,"min":0.00161355,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":7},"run_count":7,"token_priced_attempt_count":7,"total":0.016316724999999997},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.0117399875,"median":0.011861425,"min":0.0087063,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.0939199}},"codegen_cost_usd":{"admitted_cell_count":23,"cell_count":23,"cost_basis_counts":{"local_standard_estimate":23},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.014153675,"mean":0.0061271967391304345,"median":0.0038602999999999997,"min":0.00161355,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":23},"run_count":23,"token_priced_attempt_count":23,"total":0.140925525},"codegen_output_tokens":{"attempt_count":23,"output_max":26534,"output_mean":10310.565217391304,"output_min":1431,"run_count":23},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":26534,"output_mean":21543.25,"output_min":15583,"run_count":8},"medium":{"attempt_count":8,"output_max":6895,"output_mean":5735.5,"output_min":3866,"run_count":8},"none":{"attempt_count":7,"output_max":4321,"output_mean":2701.8571428571427,"output_min":1431,"run_count":7}},"display_name":"GPT-6 Luna","economics":{"all":32.22154750194082,"highest":43.98252504215083,"medium":29.48488999193139,"none":23.66554104270245},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":24,"effective_max_output_tokens":[65536],"finish_reason_observations":23,"finish_reasons":["stop"],"indexed_attempts":24,"output_token_observations":23,"provider_post_attempt_observations":24,"provider_post_attempts":24,"reasoning_token_observations":23,"reconciliation_get_attempt_observations":24,"requested_max_output_token_observations":24,"requested_max_output_tokens":[65536],"total_output_tokens":237143,"total_reasoning_output_tokens":163396,"total_visible_output_tokens":73747,"visible_token_observations":23},"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":65536,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":7,"first_pass_admitted":7,"first_pass_rate":1.0,"infra_excluded_game_aliases":["GB2-07"],"infra_failures_excluded":1,"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}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"gpt-6-luna","is_recent_addition":false,"last_measured_at":"2026-09-26T06:49:51Z","match_totals_all":{"draws":562,"losses":978,"wins":624},"match_totals_tracks":{"highest":{"draws":106,"losses":274,"wins":364},"medium":{"draws":228,"losses":363,"wins":157},"none":{"draws":228,"losses":341,"wins":103}},"model_slug":"gpt-6-luna","overall":{"max":78.76700124421147,"mean":32.37765202559489,"min":11.16952548711801},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":42,"overall_ranking_status":"partial","per_game":{"GB2-01":30.31423135991028,"GB2-02":34.631594057293064,"GB2-03":31.41183664914239,"GB2-04":35.990574437131684,"GB2-05":52.820451334431006,"GB2-06":78.76700124421147,"GB2-07":34.84826615893265,"GB2-08":53.07624509615416},"per_game_all":{"GB2-01":29.04208443364352,"GB2-02":19.37801347471418,"GB2-03":29.823211077723972,"GB2-04":21.80463036978257,"GB2-05":48.55040202053601,"GB2-06":46.34704779935881,"GB2-08":30.605443337826667},"per_game_match_totals_all":{"GB2-01":{"draws":44,"losses":156,"wins":64},"GB2-02":{"draws":222,"losses":49,"wins":39},"GB2-03":{"draws":26,"losses":111,"wins":61},"GB2-04":{"draws":140,"losses":82,"wins":52},"GB2-05":{"draws":0,"losses":134,"wins":136},"GB2-06":{"draws":20,"losses":180,"wins":112},"GB2-07":{"draws":0,"losses":125,"wins":79},"GB2-08":{"draws":110,"losses":141,"wins":81}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":56,"wins":28},"GB2-02":{"draws":53,"losses":9,"wins":36},"GB2-03":{"draws":3,"losses":42,"wins":23},"GB2-04":{"draws":37,"losses":17,"wins":32},"GB2-05":{"draws":0,"losses":38,"wins":54},"GB2-06":{"draws":9,"losses":13,"wins":84},"GB2-07":{"draws":0,"losses":66,"wins":36},"GB2-08":{"draws":4,"losses":33,"wins":71}},"medium":{"GB2-01":{"draws":29,"losses":39,"wins":20},"GB2-02":{"draws":81,"losses":23,"wins":2},"GB2-03":{"draws":13,"losses":34,"wins":19},"GB2-04":{"draws":51,"losses":28,"wins":11},"GB2-05":{"draws":0,"losses":40,"wins":46},"GB2-06":{"draws":11,"losses":79,"wins":16},"GB2-07":{"draws":0,"losses":59,"wins":43},"GB2-08":{"draws":43,"losses":61,"wins":0}},"none":{"GB2-01":{"draws":15,"losses":61,"wins":16},"GB2-02":{"draws":88,"losses":17,"wins":1},"GB2-03":{"draws":10,"losses":35,"wins":19},"GB2-04":{"draws":52,"losses":37,"wins":9},"GB2-05":{"draws":0,"losses":56,"wins":36},"GB2-06":{"draws":0,"losses":88,"wins":12},"GB2-08":{"draws":63,"losses":47,"wins":10}}},"per_game_raw_elo_all":{"GB2-01":1317.8729038019794,"GB2-02":1504.740877506323,"GB2-03":1439.156726706736,"GB2-04":1489.3638425749934,"GB2-05":1505.7095506082678,"GB2-06":1444.4680040907597,"GB2-08":1435.832605797209},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1336.4235439160918,"GB2-02":1614.6377800900714,"GB2-03":1455.3760991344245,"GB2-04":1583.0598086290083,"GB2-05":1573.1332727870044,"GB2-06":1981.0510659963124,"GB2-07":1327.506734017364,"GB2-08":1725.9036816398757},"medium":{"GB2-01":1403.469925081895,"GB2-02":1448.5149040010224,"GB2-03":1447.1990224682556,"GB2-04":1466.4734033616608,"GB2-05":1482.5774284119188,"GB2-06":1238.1322772964918,"GB2-07":1433.9594677677337,"GB2-08":1266.6523897681761},"none":{"GB2-01":1213.725242407951,"GB2-02":1451.069948427875,"GB2-03":1414.8950585175285,"GB2-04":1418.5583157343112,"GB2-05":1461.4179506258806,"GB2-06":1114.2206689794748,"GB2-08":1314.9417459835747}},"per_game_tracks":{"highest":{"GB2-01":30.31423135991028,"GB2-02":34.631594057293064,"GB2-03":31.41183664914239,"GB2-04":35.990574437131684,"GB2-05":52.820451334431006,"GB2-06":78.76700124421147,"GB2-07":34.84826615893265,"GB2-08":53.07624509615416},"medium":{"GB2-01":35.23563861244414,"GB2-02":11.57224093338897,"GB2-03":30.578270497969736,"GB2-04":18.253791185098006,"GB2-05":47.03655371801389,"GB2-06":33.9119386787579,"GB2-07":41.897343871885134,"GB2-08":17.39334243789331},"none":{"GB2-01":21.576383328576128,"GB2-02":11.93020543346051,"GB2-03":27.47952608605979,"GB2-04":11.16952548711801,"GB2-05":45.79420100916315,"GB2-06":26.362203475107076,"GB2-08":21.346742479432535}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.98252504215083,"medium":29.48488999193139,"none":23.66554104270245},"reasoning_agg":{"highest":{"max":78.76700124421147,"mean":43.98252504215083,"min":30.31423135991028},"medium":{"max":47.03655371801389,"mean":29.48488999193139,"min":11.57224093338897},"none":{"max":45.79420100916315,"mean":23.66554104270245,"min":11.16952548711801}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":78.76700124421147,"expected_score":30.707357658555704,"reasoning_variance":20.316983999448382,"reliability_score":91.77668684720734,"uncertainty_avg":8.223313152792654,"uncertainty_penalty":-1.6702943670391868},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":78.76700124421147,"expected_score":38.0342434073983,"reliability_score":91.79684426744055,"uncertainty_avg":8.203155732559457,"uncertainty_penalty":-5.948281634752533},"medium":{"ceiling_score":47.03655371801389,"expected_score":29.383323209016716,"reliability_score":91.89504984791701,"uncertainty_avg":8.104950152082994,"uncertainty_penalty":-0.10156678291467358},"none":{"ceiling_score":45.79420100916315,"expected_score":25.773965349572105,"reliability_score":92.39176329315208,"uncertainty_avg":7.608236706847921,"uncertainty_penalty":2.1084243068696544}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-max:73b0c0f94bcd24fa","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.9112224999999999},"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":34.36333693293443,"none":32.50605332668072},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T04:53:08Z","match_totals_all":{"draws":1084,"losses":1177,"wins":1006},"match_totals_tracks":{"medium":{"draws":604,"losses":570,"wins":559},"none":{"draws":480,"losses":607,"wins":447}},"model_slug":"qwen-qwen3-7-max","overall":{"max":72.59423998213232,"mean":32.33697424506643,"min":9.93904462148396},"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":43,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":113,"losses":159,"wins":124},"GB2-02":{"draws":373,"losses":62,"wins":35},"GB2-03":{"draws":94,"losses":48,"wins":12},"GB2-04":{"draws":151,"losses":49,"wins":43},"GB2-05":{"draws":0,"losses":274,"wins":236},"GB2-06":{"draws":25,"losses":254,"wins":191},"GB2-07":{"draws":0,"losses":126,"wins":340},"GB2-08":{"draws":328,"losses":205,"wins":25}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":62,"losses":120,"wins":24},"GB2-02":{"draws":206,"losses":33,"wins":11},"GB2-04":{"draws":151,"losses":49,"wins":43},"GB2-05":{"draws":0,"losses":145,"wins":131},"GB2-06":{"draws":23,"losses":84,"wins":131},"GB2-07":{"draws":0,"losses":37,"wins":201},"GB2-08":{"draws":162,"losses":102,"wins":18}},"none":{"GB2-01":{"draws":51,"losses":39,"wins":100},"GB2-02":{"draws":167,"losses":29,"wins":24},"GB2-03":{"draws":94,"losses":48,"wins":12},"GB2-05":{"draws":0,"losses":129,"wins":105},"GB2-06":{"draws":2,"losses":170,"wins":60},"GB2-07":{"draws":0,"losses":89,"wins":139},"GB2-08":{"draws":166,"losses":103,"wins":7}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1190.3749714106555,"GB2-02":1458.7096648243682,"GB2-04":1395.9421743428836,"GB2-05":1399.2330097720346,"GB2-06":1602.4493921742971,"GB2-07":1883.9940545010365,"GB2-08":1318.401297195483},"none":{"GB2-01":1679.322325822682,"GB2-02":1457.645853166888,"GB2-03":1307.231158203488,"GB2-05":1355.3215903048479,"GB2-06":1052.2515706157224,"GB2-07":1611.4241853485041,"GB2-08":1282.8753134299095}},"per_game_tracks":{"medium":{"GB2-01":20.87656678380296,"GB2-02":14.880930431936347,"GB2-04":9.93904462148396,"GB2-05":42.98027849366913,"GB2-06":56.680800022546194,"GB2-07":72.59423998213232,"GB2-08":22.5914981949701},"none":{"GB2-01":56.16398667264654,"GB2-02":14.49944255784443,"GB2-03":19.024448546336703,"GB2-05":40.08897544109291,"GB2-06":23.441627577324773,"GB2-07":54.5082236273668,"GB2-08":19.815668864152897}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":33.23512707565209,"none":31.438821414480778},"reasoning_agg":{"medium":{"max":72.59423998213232,"mean":33.23512707565209,"min":9.93904462148396},"none":{"max":56.16398667264654,"mean":31.438821414480778,"min":14.49944255784443}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":72.59423998213232,"reasoning_variance":1.79630566117131},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":72.59423998213232,"expected_score":34.58037819755046,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.3452511218983716},"none":{"ceiling_score":56.16398667264654,"expected_score":34.057220495481296,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.6183990810005184}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-4-1:66990b9a341d522b","codegen_cost_by_reasoning":{"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":false,"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":0.457564}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":11},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.457564},"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":30.680698980637484},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T01:38:07Z","match_totals_all":{"draws":631,"losses":680,"wins":522},"match_totals_tracks":{"none":{"draws":631,"losses":680,"wins":522}},"model_slug":"gpt-4-1","overall":{"max":56.45579481933182,"mean":30.680698980637484,"min":6.4049013625411595},"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":44,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":16,"losses":70,"wins":115},"GB2-02":{"draws":213,"losses":34,"wins":1},"GB2-03":{"draws":43,"losses":70,"wins":59},"GB2-04":{"draws":168,"losses":53,"wins":11},"GB2-05":{"draws":0,"losses":168,"wins":42},"GB2-06":{"draws":19,"losses":97,"wins":126},"GB2-07":{"draws":0,"losses":121,"wins":135},"GB2-08":{"draws":172,"losses":67,"wins":33}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":16,"losses":70,"wins":115},"GB2-02":{"draws":213,"losses":34,"wins":1},"GB2-03":{"draws":43,"losses":70,"wins":59},"GB2-04":{"draws":168,"losses":53,"wins":11},"GB2-05":{"draws":0,"losses":168,"wins":42},"GB2-06":{"draws":19,"losses":97,"wins":126},"GB2-07":{"draws":0,"losses":121,"wins":135},"GB2-08":{"draws":172,"losses":67,"wins":33}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1682.55714132983,"GB2-02":1432.20593843729,"GB2-03":1467.8051622860353,"GB2-04":1373.4991536391794,"GB2-05":981.472472393549,"GB2-06":1439.3305004809554,"GB2-07":1521.7623110628958,"GB2-08":1352.3446030968134}},"per_game_tracks":{"none":{"GB2-01":56.45579481933182,"GB2-02":11.153552195821447,"GB2-03":34.24073193991496,"GB2-04":6.4049013625411595,"GB2-05":16.48519907368788,"GB2-06":46.84511336903042,"GB2-07":48.66909873351094,"GB2-08":25.191200351261255}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":30.680698980637484},"reasoning_agg":{"none":{"max":56.45579481933182,"mean":30.680698980637484,"min":6.4049013625411595}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":56.45579481933182},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":56.45579481933182,"expected_score":32.519010782931716,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.838311802294232}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-6-luna:2e545312142d8002","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"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},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"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":0.05054445},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.036787799999999996}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"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":0.05054445},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.0057713,"mean":0.004598475,"median":0.0045067,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.036787799999999996},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.030833324999999998,"median":0.031411375,"min":0.0247604,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8},"run_count":8,"token_priced_attempt_count":8,"total":0.2466666}},"codegen_cost_usd":{"admitted_cell_count":24,"cell_count":24,"cost_basis_counts":{"local_standard_estimate":25},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.0377622,"mean":0.01391661875,"median":0.00586915,"min":0.0040101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":25},"run_count":24,"token_priced_attempt_count":25,"total":0.33399885},"codegen_output_tokens":{"attempt_count":25,"output_max":29793,"output_mean":9924.083333333334,"output_min":1845,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":8,"output_max":29793,"output_mean":24080.5,"output_min":19109,"run_count":8},"medium":{"attempt_count":9,"output_max":6277,"output_mean":3473.625,"output_min":2113,"run_count":8},"none":{"attempt_count":8,"output_max":2721,"output_mean":2218.125,"output_min":1845,"run_count":8}},"display_name":"GPT-5.6 Luna","economics":{"all":30.48221935864308,"highest":40.72382489562966,"medium":31.575706011955152,"none":19.147127168344415},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":25,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"total_output_tokens":238178,"total_reasoning_output_tokens":167062,"total_visible_output_tokens":71116,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":null,"stream":null,"temperature":null},"prompt_identity":"unknown_legacy","prompt_profile":"unknown_legacy","provider":"openai","provider_model":"gpt-5.6-luna","provider_reasoning_params":{"bracket":"aggregate","request_mode":null,"requested_effort":null,"source":"versioned_reasoning_capability_catalog","track_id":"overall"},"provider_route":"openai","provider_setting_label":null,"reasoning_bracket":null,"reasoning_bucket":"aggregate","reasoning_bucket_label":"Aggregate of public reasoning variants","reasoning_catalog_sha256":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":7,"first_pass_rate":0.875,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true},"repaired_admitted":1,"repaired_rate":0.125},"baseline":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}},"intensive":{"admitted_plugins":8,"evaluated_cells":8,"first_pass_admitted":8,"first_pass_rate":1.0,"model_code_failure_rate":0.0,"model_code_failures":0,"official_qualification":{"fixed_coverage_complete":true,"generation_complete":true,"generation_quality_qualified":true,"grouped_coverage_state":"stable","grouped_stable":true,"policy_id":"duellab_official_qualification_v1","ranked":true}}},"id":"gpt-5.6-luna","is_recent_addition":false,"last_measured_at":"2026-09-26T05:41:30Z","match_totals_all":{"draws":2717,"losses":3319,"wins":2220},"match_totals_tracks":{"highest":{"draws":922,"losses":770,"wins":1078},"medium":{"draws":963,"losses":1108,"wins":811},"none":{"draws":832,"losses":1441,"wins":331}},"model_slug":"gpt-5-6-luna","overall":{"max":78.8933106913037,"mean":30.482219358643075,"min":4.225576109546502},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":45,"overall_ranking_status":"ranked","per_game":{"GB2-01":64.79502706024216,"GB2-02":10.566580353970428,"GB2-03":23.50169824726778,"GB2-04":11.938408850855591,"GB2-05":53.11988565154375,"GB2-06":78.8933106913037,"GB2-07":62.946517435493995,"GB2-08":20.0291708743599},"per_game_all":{"GB2-01":42.39741293314845,"GB2-02":13.260031612519297,"GB2-03":23.4663745036425,"GB2-04":17.178351499390786,"GB2-05":41.795580755329304,"GB2-06":52.75027499781327,"GB2-07":37.81974148240878,"GB2-08":15.189987084892243},"per_game_match_totals_all":{"GB2-01":{"draws":132,"losses":486,"wins":421},"GB2-02":{"draws":828,"losses":107,"wins":23},"GB2-03":{"draws":492,"losses":407,"wins":171},"GB2-04":{"draws":623,"losses":200,"wins":111},"GB2-05":{"draws":0,"losses":566,"wins":503},"GB2-06":{"draws":81,"losses":477,"wins":532},"GB2-07":{"draws":0,"losses":628,"wins":418},"GB2-08":{"draws":561,"losses":448,"wins":41}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":84,"wins":236},"GB2-02":{"draws":259,"losses":26,"wins":15},"GB2-03":{"draws":174,"losses":145,"wins":68},"GB2-04":{"draws":188,"losses":83,"wins":33},"GB2-05":{"draws":0,"losses":191,"wins":245},"GB2-06":{"draws":44,"losses":50,"wins":237},"GB2-07":{"draws":0,"losses":110,"wins":238},"GB2-08":{"draws":257,"losses":81,"wins":6}},"medium":{"GB2-01":{"draws":60,"losses":206,"wins":143},"GB2-02":{"draws":299,"losses":47,"wins":6},"GB2-03":{"draws":135,"losses":146,"wins":88},"GB2-04":{"draws":213,"losses":55,"wins":44},"GB2-05":{"draws":0,"losses":158,"wins":161},"GB2-06":{"draws":17,"losses":165,"wins":233},"GB2-07":{"draws":0,"losses":234,"wins":118},"GB2-08":{"draws":239,"losses":97,"wins":18}},"none":{"GB2-01":{"draws":72,"losses":196,"wins":42},"GB2-02":{"draws":270,"losses":34,"wins":2},"GB2-03":{"draws":183,"losses":116,"wins":15},"GB2-04":{"draws":222,"losses":62,"wins":34},"GB2-05":{"draws":0,"losses":217,"wins":97},"GB2-06":{"draws":20,"losses":262,"wins":62},"GB2-07":{"draws":0,"losses":284,"wins":62},"GB2-08":{"draws":65,"losses":270,"wins":17}}},"per_game_raw_elo_all":{"GB2-01":1481.660401942867,"GB2-02":1444.2839518122157,"GB2-03":1343.691477205759,"GB2-04":1440.1671051007572,"GB2-05":1377.7072325081015,"GB2-06":1532.5088723800152,"GB2-07":1354.3592508978766,"GB2-08":1220.5654420513529},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1792.0189545539636,"GB2-02":1425.7229542171106,"GB2-03":1343.1620240705038,"GB2-04":1406.2733995796266,"GB2-05":1555.550717864032,"GB2-06":1966.426477840449,"GB2-07":1733.835145202923,"GB2-08":1283.1290891065676},"medium":{"GB2-01":1379.51674140029,"GB2-02":1473.1868681480432,"GB2-03":1386.3819000728995,"GB2-04":1499.7063488522076,"GB2-05":1369.2298828228195,"GB2-06":1544.2102078313465,"GB2-07":1237.9987036210925,"GB2-08":1299.4014875977803},"none":{"GB2-01":1273.4455098743485,"GB2-02":1433.942033071494,"GB2-03":1301.5305074738733,"GB2-04":1414.521566870438,"GB2-05":1208.3410968374528,"GB2-06":1086.8899314682499,"GB2-07":1091.2439038696145,"GB2-08":1079.1657494497108}},"per_game_tracks":{"highest":{"GB2-01":64.79502706024216,"GB2-02":10.566580353970428,"GB2-03":23.50169824726778,"GB2-04":11.938408850855591,"GB2-05":53.11988565154375,"GB2-06":78.8933106913037,"GB2-07":62.946517435493995,"GB2-08":20.0291708743599},"medium":{"GB2-01":35.14102929651951,"GB2-02":17.46371184147461,"GB2-03":27.508190630192537,"GB2-04":26.315108334069258,"GB2-05":41.198476110358186,"GB2-06":53.54259794154895,"GB2-07":30.12131967070786,"GB2-08":21.315214270770326},"none":{"GB2-01":27.256182442683677,"GB2-02":11.749802642112853,"GB2-03":19.38923463346718,"GB2-04":13.28153731324751,"GB2-05":31.068380504085983,"GB2-06":25.81491636058714,"GB2-07":20.391387341024483,"GB2-08":4.225576109546502}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":40.72382489562966,"medium":31.575706011955152,"none":19.147127168344415},"reasoning_agg":{"highest":{"max":78.8933106913037,"mean":40.72382489562966,"min":10.566580353970428},"medium":{"max":53.54259794154895,"mean":31.575706011955152,"min":17.46371184147461},"none":{"max":31.068380504085983,"mean":19.147127168344415,"min":4.225576109546502}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":78.8933106913037,"expected_score":26.913167708149846,"reasoning_variance":21.576697727285246,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.569051650493229},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":78.8933106913037,"expected_score":32.20936979804318,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.514455097586485},"medium":{"ceiling_score":53.54259794154895,"expected_score":30.095328713644317,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.4803772983108345},"none":{"ceiling_score":31.068380504085983,"expected_score":18.43480461276205,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7123225555823645}}},{"canonical_public_row_identity":"publication-row.v1:overall:o3:bb9ab27740359998","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":19,"cell_count":8,"cost_basis_counts":{"estimated":32,"local_standard_estimate":8},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8,"boardgame-list-prices-2026-09-08":32},"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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-2026-09-08":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},"cost_is_complete":false,"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},"cost_is_complete":false,"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-2026-09-08":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},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":13,"max":0.1097735,"mean":0.091486,"median":0.08840575,"min":0.0773785,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":8,"boardgame-list-prices-2026-09-08":32},"recorded_attempt_count":32,"run_count":32,"token_priced_attempt_count":8,"total":2.9275520000000004}},"codegen_cost_usd":{"admitted_cell_count":29,"cell_count":24,"cost_basis_counts":{"estimated":40,"local_standard_estimate":29},"cost_is_complete":false,"evidence_basis":"Combined: Recorded attempt + Standard list-price estimate","failed_cell_count":19,"max":0.17217,"mean":0.08358424999999998,"median":0.08653749999999999,"min":0.037309999999999996,"pricing_table_versions":{"boardgame-list-prices-2026-07-12":13,"boardgame-list-prices-2026-08-08":16,"boardgame-list-prices-2026-09-08":40},"recorded_attempt_count":40,"run_count":48,"token_priced_attempt_count":29,"total":4.201686},"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":36.445249851562046,"highest":39.670558602078806,"medium":36.80451551318272,"none":26.398633585670154},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T03:57:49Z","match_totals_all":{"draws":1715,"losses":5126,"wins":4315},"match_totals_tracks":{"highest":{"draws":856,"losses":3705,"wins":3475},"medium":{"draws":409,"losses":533,"wins":536},"none":{"draws":450,"losses":888,"wins":304}},"model_slug":"o3","overall":{"max":52.99565138337291,"mean":30.424073657093132,"min":7.417796964596298},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":46,"overall_ranking_status":"partial","per_game":{"GB2-01":46.68796632195034,"GB2-03":18.36417652244065,"GB2-05":51.82356301713207,"GB2-06":45.33761895416281,"GB2-07":41.76874695076019,"GB2-08":34.04127984602672},"per_game_all":{"GB2-01":32.31880690896483,"GB2-06":39.96402966615908,"GB2-07":44.96726620015861,"GB2-08":28.53089663096566},"per_game_match_totals_all":{"GB2-01":{"draws":265,"losses":787,"wins":640},"GB2-03":{"draws":124,"losses":180,"wins":90},"GB2-04":{"draws":202,"losses":44,"wins":14},"GB2-05":{"draws":0,"losses":861,"wins":974},"GB2-06":{"draws":110,"losses":1335,"wins":982},"GB2-07":{"draws":0,"losses":1338,"wins":1218},"GB2-08":{"draws":1014,"losses":581,"wins":397}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":113,"losses":436,"wins":543},"GB2-03":{"draws":124,"losses":180,"wins":90},"GB2-05":{"draws":0,"losses":749,"wins":860},"GB2-06":{"draws":35,"losses":938,"wins":808},"GB2-07":{"draws":0,"losses":1031,"wins":857},"GB2-08":{"draws":584,"losses":371,"wins":317}},"medium":{"GB2-01":{"draws":37,"losses":90,"wins":75},"GB2-04":{"draws":202,"losses":44,"wins":14},"GB2-05":{"draws":0,"losses":112,"wins":114},"GB2-06":{"draws":22,"losses":109,"wins":119},"GB2-07":{"draws":0,"losses":95,"wins":155},"GB2-08":{"draws":148,"losses":83,"wins":59}},"none":{"GB2-01":{"draws":115,"losses":261,"wins":22},"GB2-06":{"draws":53,"losses":288,"wins":55},"GB2-07":{"draws":0,"losses":212,"wins":206},"GB2-08":{"draws":282,"losses":127,"wins":21}}},"per_game_raw_elo_all":{"GB2-01":1343.7613122293142,"GB2-06":1321.128825554043,"GB2-07":1461.994604464972,"GB2-08":1391.9147827175786},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1540.324188438851,"GB2-03":1288.1863481775406,"GB2-05":1535.734670325432,"GB2-06":1407.6611765662142,"GB2-07":1411.0774231343432,"GB2-08":1461.6883682594096},"medium":{"GB2-01":1385.9328500647798,"GB2-04":1378.6571387984002,"GB2-05":1505.3533994066024,"GB2-06":1460.9970419106069,"GB2-07":1587.396874537179,"GB2-08":1384.3844517880543},"none":{"GB2-01":1105.0268981843121,"GB2-06":1094.728258185308,"GB2-07":1387.5095157233932,"GB2-08":1329.6715281052718}},"per_game_tracks":{"highest":{"GB2-01":46.68796632195034,"GB2-03":18.36417652244065,"GB2-05":51.82356301713207,"GB2-06":45.33761895416281,"GB2-07":41.76874695076019,"GB2-08":34.04127984602672},"medium":{"GB2-01":35.00331062048653,"GB2-04":7.417796964596298,"GB2-05":49.496444311336134,"GB2-06":48.17815939083763,"GB2-07":52.99565138337291,"GB2-08":27.735730408466818},"none":{"GB2-01":15.26514378445762,"GB2-06":26.376310653476803,"GB2-07":40.13740026634274,"GB2-08":23.81567963840345}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.82324364802661,"medium":34.250460973466446,"none":22.198516349786345},"reasoning_agg":{"highest":{"max":51.82356301713207,"mean":34.82324364802661,"min":18.36417652244065},"medium":{"max":52.99565138337291,"mean":34.250460973466446,"min":7.417796964596298},"none":{"max":40.13740026634274,"mean":22.198516349786345,"min":15.26514378445762}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":52.99565138337291,"expected_score":32.235301792080136,"reasoning_variance":12.624727298240266,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.8112281349870045},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.82356301713207,"expected_score":28.83999168544753,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.983251962579082},"medium":{"ceiling_score":52.99565138337291,"expected_score":37.60382800113394,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.3533670276674954},"none":{"ceiling_score":40.13740026634274,"expected_score":23.970152655534136,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7716363057477906}}},{"canonical_public_row_identity":"publication-row.v1:overall:moonshotai-kimi-k2-7-code:0ddc5bc5de1cd512","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031540000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.226689264,"mean":0.16037539425,"median":0.140728509,"min":0.10689655,"recorded_attempt_count":18,"run_count":8,"total":1.2830031540000002},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"medium":32.405981300695416},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T05:02:47Z","match_totals_all":{"draws":399,"losses":471,"wins":516},"match_totals_tracks":{"medium":{"draws":399,"losses":471,"wins":516}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":52.10024891979631,"mean":30.15716366239893,"min":10.084015620241896},"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":47,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":7,"losses":104,"wins":95},"GB2-02":{"draws":199,"losses":41,"wins":12},"GB2-04":{"draws":168,"losses":44,"wins":18},"GB2-05":{"draws":0,"losses":98,"wins":106},"GB2-07":{"draws":0,"losses":112,"wins":134},"GB2-08":{"draws":25,"losses":72,"wins":151}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":104,"wins":95},"GB2-02":{"draws":199,"losses":41,"wins":12},"GB2-04":{"draws":168,"losses":44,"wins":18},"GB2-05":{"draws":0,"losses":98,"wins":106},"GB2-07":{"draws":0,"losses":112,"wins":134},"GB2-08":{"draws":25,"losses":72,"wins":151}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1315.6530574082221,"GB2-02":1446.5135225765007,"GB2-04":1397.5979910044068,"GB2-05":1548.1414093854123,"GB2-07":1416.3656604436499,"GB2-08":1640.6649953019173}},"per_game_tracks":{"medium":{"GB2-01":29.939058381985696,"GB2-02":13.186246582543763,"GB2-04":10.084015620241896,"GB2-05":52.10024891979631,"GB2-07":41.65683864784393,"GB2-08":47.46947965176091}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.15716366239893},"reasoning_agg":{"medium":{"max":52.10024891979631,"mean":30.15716366239893,"min":10.084015620241896}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":52.10024891979631},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":52.10024891979631,"expected_score":33.846699422331355,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.6895357599324257}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-mini:597c0fcc8f6fc41d","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"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":1,"boardgame-list-prices-2026-09-08":2},"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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.325659,"mean":0.25189603125,"median":0.25775625,"min":0.169101,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":9},"run_count":8,"token_priced_attempt_count":9,"total":2.01516825},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","max":0.03021,"mean":0.0183815625,"median":0.015581250000000001,"min":0.01245825,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":10},"run_count":8,"token_priced_attempt_count":10,"total":0.1470525}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":9},"cost_is_complete":false,"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},"historical-provider-setting-baseline":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"local_standard_estimate":10},"cost_is_complete":false,"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},"cost_is_complete":false,"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":1,"boardgame-list-prices-2026-09-08":2},"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},"cost_is_complete":false,"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":20,"boardgame-list-prices-2026-09-08":2},"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":37.28394178026495,"none":21.26358867272033},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T06:41:56Z","match_totals_all":{"draws":1289,"losses":1298,"wins":894},"match_totals_tracks":{"medium":{"draws":540,"losses":578,"wins":669},"none":{"draws":749,"losses":720,"wins":225}},"model_slug":"gpt-5-4-mini","overall":{"max":59.83834188762664,"mean":29.273765226492642,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":48,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":91,"losses":133,"wins":160},"GB2-02":{"draws":384,"losses":52,"wins":6},"GB2-03":{"draws":208,"losses":65,"wins":40},"GB2-04":{"draws":300,"losses":78,"wins":84},"GB2-05":{"draws":0,"losses":242,"wins":166},"GB2-06":{"draws":35,"losses":209,"wins":206},"GB2-07":{"draws":0,"losses":353,"wins":159},"GB2-08":{"draws":271,"losses":166,"wins":73}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":12,"losses":56,"wins":126},"GB2-02":{"draws":184,"losses":30,"wins":6},"GB2-03":{"draws":76,"losses":52,"wins":35},"GB2-04":{"draws":147,"losses":32,"wins":49},"GB2-05":{"draws":0,"losses":96,"wins":122},"GB2-06":{"draws":25,"losses":82,"wins":125},"GB2-07":{"draws":0,"losses":123,"wins":139},"GB2-08":{"draws":96,"losses":107,"wins":67}},"none":{"GB2-01":{"draws":79,"losses":77,"wins":34},"GB2-02":{"draws":200,"losses":22,"wins":0},"GB2-03":{"draws":132,"losses":13,"wins":5},"GB2-04":{"draws":153,"losses":46,"wins":35},"GB2-05":{"draws":0,"losses":146,"wins":44},"GB2-06":{"draws":10,"losses":127,"wins":81},"GB2-07":{"draws":0,"losses":230,"wins":20},"GB2-08":{"draws":175,"losses":59,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1729.817494130198,"GB2-02":1419.3250499564451,"GB2-03":1429.6801011302036,"GB2-04":1487.9754130379592,"GB2-05":1517.259103007682,"GB2-06":1484.1930122041379,"GB2-07":1539.702761924633,"GB2-08":1352.191252201505},"none":{"GB2-01":1370.0049175972013,"GB2-02":1429.3624849783323,"GB2-03":1447.7911939665923,"GB2-04":1424.0077484008707,"GB2-05":1064.7393281579173,"GB2-06":1248.7114766299912,"GB2-07":787.0748754938917,"GB2-08":1319.807179411186}},"per_game_tracks":{"medium":{"GB2-01":59.83834188762664,"GB2-02":9.130656395302635,"GB2-03":30.588968784170408,"GB2-04":23.929255659421738,"GB2-05":50.215019871218,"GB2-06":49.52087161013256,"GB2-07":49.87603331793363,"GB2-08":25.172386716313994},"none":{"GB2-01":33.78827434519667,"GB2-02":10.553854448605595,"GB2-03":32.16358719584539,"GB2-04":14.169464639251505,"GB2-05":21.63378493673125,"GB2-06":35.2534607882226,"GB2-07":0.0,"GB2-08":22.546283027909663}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":37.28394178026495,"none":21.26358867272033},"reasoning_agg":{"medium":{"max":59.83834188762664,"mean":37.28394178026495,"min":9.130656395302635},"none":{"max":35.2534607882226,"mean":21.26358867272033,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":59.83834188762664,"reasoning_variance":16.020353107544622},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":59.83834188762664,"expected_score":36.6704768025541,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.613464977710855},"none":{"ceiling_score":35.2534607882226,"expected_score":22.17164674826228,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.9080580755419483}}},{"canonical_public_row_identity":"publication-row.v1:overall:bytedance-seed-seed-2-0-code:38ab75f9172dbd13","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.075846,"mean":0.050721249999999996,"median":0.04471025,"min":0.0372345,"recorded_attempt_count":11,"run_count":8,"total":0.40576999999999996},"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.071558,"mean":0.053513000000000005,"median":0.0517895,"min":0.034152,"recorded_attempt_count":14,"run_count":8,"total":0.428104},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.030187,"mean":0.020951124999999998,"median":0.0183875,"min":0.0121355,"recorded_attempt_count":9,"run_count":8,"total":0.16760899999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.071558,"mean":0.053513000000000005,"median":0.0517895,"min":0.034152,"recorded_attempt_count":14,"run_count":8,"total":0.42810399999999993},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":9},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.030187,"mean":0.020951124999999998,"median":0.0183875,"min":0.0121355,"recorded_attempt_count":9,"run_count":8,"total":0.167609},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.075846,"mean":0.050721249999999996,"median":0.04471025,"min":0.0372345,"recorded_attempt_count":11,"run_count":8,"total":0.40576999999999996}},"codegen_cost_usd":{"admitted_cell_count":22,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.075846,"mean":0.041728458333333336,"median":0.04202725,"min":0.0121355,"recorded_attempt_count":34,"run_count":24,"total":1.001483},"codegen_latency_ms":{"attempt_count":34,"max_ms":395404,"mean_ms":199903.16666666666,"min_ms":55601,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":395404,"mean_ms":251379.375,"min_ms":180439,"run_count":8},"medium":{"attempt_count":14,"max_ms":353826,"mean_ms":258198.75,"min_ms":158866,"run_count":8},"none":{"attempt_count":9,"max_ms":131809,"mean_ms":90131.375,"min_ms":55601,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":22808,"output_mean":12018.333333333334,"output_min":2752,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":22808,"output_mean":15068.125,"output_min":11085,"run_count":8},"medium":{"attempt_count":14,"output_max":21381,"output_mean":15556.75,"output_min":10057,"run_count":8},"none":{"attempt_count":9,"output_max":8609,"output_mean":5430.125,"output_min":2752,"run_count":8}},"display_name":"Seed 2.0 Code","economics":{"all":31.251973527748934,"highest":32.03617042182406,"medium":35.29136230119987,"none":22.370178519942232},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":157,"total_output_tokens":288440,"total_reasoning_output_tokens":204471,"total_visible_output_tokens":83969,"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":"bytedance-seed","provider_model":"bytedance-seed/seed-2.0-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":2,"first_pass_rate":0.25,"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":5,"repaired_rate":0.625},"baseline":{"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}},"intensive":{"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":"bytedance-seed/seed-2.0-code","is_recent_addition":false,"last_measured_at":"2026-09-26T07:10:13Z","match_totals_all":{"draws":1824,"losses":2468,"wins":1594},"match_totals_tracks":{"highest":{"draws":778,"losses":865,"wins":637},"medium":{"draws":495,"losses":674,"wins":607},"none":{"draws":551,"losses":929,"wins":350}},"model_slug":"bytedance-seed-seed-2-0-code","overall":{"max":74.74556215443342,"mean":29.26819321712237,"min":7.821657865946365},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":49,"overall_ranking_status":"ranked","per_game":{"GB2-01":37.75243763955775,"GB2-02":7.821657865946365,"GB2-03":26.556040491228302,"GB2-04":12.964843064935756,"GB2-05":54.97499777815619,"GB2-06":24.907776352459393,"GB2-07":51.39429705964525,"GB2-08":39.917313122663465},"per_game_all":{"GB2-01":35.1729691936371,"GB2-03":26.71220715657026,"GB2-04":14.943320135875402,"GB2-05":41.39708060893105,"GB2-06":23.798192715293908,"GB2-08":45.48807135618589},"per_game_match_totals_all":{"GB2-01":{"draws":250,"losses":323,"wins":169},"GB2-02":{"draws":421,"losses":65,"wins":4},"GB2-03":{"draws":253,"losses":377,"wins":232},"GB2-04":{"draws":546,"losses":126,"wins":68},"GB2-05":{"draws":0,"losses":461,"wins":363},"GB2-06":{"draws":5,"losses":577,"wins":158},"GB2-07":{"draws":0,"losses":355,"wins":279},"GB2-08":{"draws":349,"losses":184,"wins":321}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":135,"losses":70,"wins":49},"GB2-02":{"draws":210,"losses":25,"wins":1},"GB2-03":{"draws":110,"losses":122,"wins":72},"GB2-04":{"draws":169,"losses":48,"wins":21},"GB2-05":{"draws":0,"losses":163,"wins":167},"GB2-06":{"draws":1,"losses":183,"wins":60},"GB2-07":{"draws":0,"losses":185,"wins":173},"GB2-08":{"draws":153,"losses":69,"wins":94}},"medium":{"GB2-01":{"draws":46,"losses":106,"wins":102},"GB2-02":{"draws":211,"losses":40,"wins":3},"GB2-03":{"draws":57,"losses":131,"wins":62},"GB2-04":{"draws":178,"losses":48,"wins":24},"GB2-05":{"draws":0,"losses":106,"wins":152},"GB2-06":{"draws":2,"losses":199,"wins":45},"GB2-08":{"draws":1,"losses":44,"wins":219}},"none":{"GB2-01":{"draws":69,"losses":147,"wins":18},"GB2-03":{"draws":86,"losses":124,"wins":98},"GB2-04":{"draws":199,"losses":30,"wins":23},"GB2-05":{"draws":0,"losses":192,"wins":44},"GB2-06":{"draws":2,"losses":195,"wins":53},"GB2-07":{"draws":0,"losses":170,"wins":106},"GB2-08":{"draws":195,"losses":71,"wins":8}}},"per_game_raw_elo_all":{"GB2-01":1385.6007023383283,"GB2-03":1380.7328584138602,"GB2-04":1428.382840502074,"GB2-05":1374.3014801151483,"GB2-06":1057.3704400184067,"GB2-08":1613.4941215439487},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1420.9107119825467,"GB2-02":1409.0576870502066,"GB2-03":1378.3355368220339,"GB2-04":1415.93505703322,"GB2-05":1587.897850776817,"GB2-06":1075.8850737768978,"GB2-07":1559.0771917914801,"GB2-08":1540.430259454854},"medium":{"GB2-01":1510.687721362051,"GB2-02":1425.928468511625,"GB2-03":1411.5589265510903,"GB2-04":1440.1094594622932,"GB2-05":1502.579690132161,"GB2-06":1028.9838276998619,"GB2-08":1991.493065988937},"none":{"GB2-01":1225.2036736703878,"GB2-03":1352.3041118684562,"GB2-04":1429.1040050107092,"GB2-05":1032.426899436467,"GB2-06":1067.24241857846,"GB2-07":1206.4806309015996,"GB2-08":1308.5590391880553}},"per_game_tracks":{"highest":{"GB2-01":37.75243763955775,"GB2-02":7.821657865946365,"GB2-03":26.556040491228302,"GB2-04":12.964843064935756,"GB2-05":54.97499777815619,"GB2-06":24.907776352459393,"GB2-07":51.39429705964525,"GB2-08":39.917313122663465},"medium":{"GB2-01":44.24681681795239,"GB2-02":10.316101937846748,"GB2-03":29.45127776485631,"GB2-04":16.76894332682516,"GB2-05":49.4285457366069,"GB2-06":22.082288369878185,"GB2-08":74.74556215443342},"none":{"GB2-01":23.51965312340115,"GB2-03":24.12930321362615,"GB2-04":15.096174015865286,"GB2-05":19.787698312030066,"GB2-06":24.40451342354415,"GB2-07":27.852568759668017,"GB2-08":21.80133879146082}},"provider_color":"#F44336","provider_company":"ByteDance","provider_key":"bytedance-seed","provider_text_color":"#fff8f8","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.03617042182406,"medium":34.13268371003617,"none":21.635725519506884},"reasoning_agg":{"highest":{"max":54.97499777815619,"mean":32.03617042182406,"min":7.821657865946365},"medium":{"max":74.74556215443342,"mean":34.13268371003617,"min":10.316101937846748},"none":{"max":27.852568759668017,"mean":21.635725519506884,"min":15.096174015865286}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":74.74556215443342,"expected_score":26.467514469072597,"reasoning_variance":12.496958190529284,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.800678748049773},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.97499777815619,"expected_score":21.798338201935167,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.237832219888894},"medium":{"ceiling_score":74.74556215443342,"expected_score":33.38414061264184,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7485430973943252},"none":{"ceiling_score":27.852568759668017,"expected_score":21.25408533342741,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.38164018607947625}}},{"canonical_public_row_identity":"publication-row.v1:overall:gpt-5-4-nano:5d223ef87df56f9e","codegen_cost_by_reasoning":{"highest":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"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":1,"boardgame-list-prices-2026-09-08":2},"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Standard list-price estimate","failed_cell_count":4,"max":0.01311555,"mean":0.009215359375,"median":0.009537575,"min":0.004854125,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":27},"run_count":16,"token_priced_attempt_count":27,"total":0.14744575000000001},"historical-provider-setting-intensive":{"cell_count":1,"cost_basis_counts":{"estimated":2,"local_standard_estimate":3},"cost_is_complete":false,"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":1,"boardgame-list-prices-2026-09-08":2},"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},"cost_is_complete":false,"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":53,"boardgame-list-prices-2026-09-08":2},"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":32.61170555250026,"none":27.42330573661719},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T06:22:57Z","match_totals_all":{"draws":1271,"losses":2355,"wins":1698},"match_totals_tracks":{"medium":{"draws":527,"losses":1184,"wins":1015},"none":{"draws":744,"losses":1171,"wins":683}},"model_slug":"gpt-5-4-nano","overall":{"max":57.7824454485622,"mean":27.934436610951053,"min":9.814032016321745},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":50,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":154,"losses":405,"wins":185},"GB2-02":{"draws":582,"losses":97,"wins":7},"GB2-03":{"draws":60,"losses":66,"wins":34},"GB2-04":{"draws":124,"losses":33,"wins":69},"GB2-05":{"draws":0,"losses":548,"wins":282},"GB2-06":{"draws":19,"losses":399,"wins":496},"GB2-07":{"draws":0,"losses":507,"wins":259},"GB2-08":{"draws":332,"losses":300,"wins":366}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":57,"losses":263,"wins":52},"GB2-02":{"draws":195,"losses":27,"wins":0},"GB2-04":{"draws":124,"losses":33,"wins":69},"GB2-05":{"draws":0,"losses":206,"wins":220},"GB2-06":{"draws":18,"losses":174,"wins":286},"GB2-07":{"draws":0,"losses":312,"wins":190},"GB2-08":{"draws":133,"losses":169,"wins":198}},"none":{"GB2-01":{"draws":97,"losses":142,"wins":133},"GB2-02":{"draws":387,"losses":70,"wins":7},"GB2-03":{"draws":60,"losses":66,"wins":34},"GB2-05":{"draws":0,"losses":342,"wins":62},"GB2-06":{"draws":1,"losses":225,"wins":210},"GB2-07":{"draws":0,"losses":195,"wins":69},"GB2-08":{"draws":199,"losses":131,"wins":168}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1078.3247496618824,"GB2-02":1424.0818518929575,"GB2-04":1515.974624140866,"GB2-05":1482.6882334696502,"GB2-06":1620.6498437258638,"GB2-07":1281.8516999457192,"GB2-08":1531.8183732196799},"none":{"GB2-01":1485.746997448452,"GB2-02":1424.847383279174,"GB2-03":1348.3065351353828,"GB2-05":931.2112750125314,"GB2-06":1368.274676243932,"GB2-07":1102.1377570186742,"GB2-08":1547.2879538438208}},"per_game_tracks":{"medium":{"GB2-01":12.6616825013361,"GB2-02":9.814032016321745,"GB2-04":28.206182294273038,"GB2-05":48.017786280784506,"GB2-06":57.7824454485622,"GB2-07":32.76639863976109,"GB2-08":39.03341168646314},"none":{"GB2-01":42.13784918223922,"GB2-02":9.997714314921211,"GB2-03":22.93230117937788,"GB2-05":13.288652706512883,"GB2-06":42.47210052304716,"GB2-07":20.907567454686376,"GB2-08":40.22695479553562}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.34861165076366,"none":25.520261571138445},"reasoning_agg":{"medium":{"max":57.7824454485622,"mean":30.34861165076366,"min":9.814032016321745},"none":{"max":42.47210052304716,"mean":25.520261571138445,"min":9.997714314921211}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":57.7824454485622,"reasoning_variance":4.828350079625217},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":57.7824454485622,"expected_score":32.967843911256686,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.6192322604930247},"none":{"ceiling_score":42.47210052304716,"expected_score":29.130480671484303,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.6102191003458586}}},{"canonical_public_row_identity":"publication-row.v1:overall:deepseek-deepseek-v4-flash:a1e016da344bef87","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01423672,"mean":0.0073094338874999994,"median":0.0062260825200000005,"min":0.004397959999999999,"recorded_attempt_count":13,"run_count":8,"total":0.058475471099999995},"medium":{"admitted_cell_count":22,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.008042989573333334,"mean":0.0037891845841666666,"median":0.0032265161666666666,"min":0.002126702,"recorded_attempt_count":36,"run_count":24,"total":0.09094043002000002},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00200925116,"mean":0.0013339496149999998,"median":0.0012586017,"min":0.0008945895,"recorded_attempt_count":10,"run_count":8,"total":0.01067159692}},"codegen_cost_by_setting":{"historical-provider-setting-balanced-variant-1":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.01663094,"mean":0.00499588742,"median":0.0034890575,"min":0.00258188,"recorded_attempt_count":12,"run_count":8,"total":0.03996709936},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":24},"cost_is_complete":false,"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":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.00200925116,"mean":0.0013339496149999998,"median":0.0012586017,"min":0.0008945895,"recorded_attempt_count":10,"run_count":8,"total":0.01067159692},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.01423672,"mean":0.0073094338874999994,"median":0.0062260825200000005,"min":0.004397959999999999,"recorded_attempt_count":13,"run_count":8,"total":0.0584754711}},"codegen_cost_usd":{"admitted_cell_count":36,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.01423672,"mean":0.004144189362222222,"median":0.0032265161666666666,"min":0.0008945895,"recorded_attempt_count":59,"run_count":40,"total":0.16008749804},"codegen_latency_ms":{"attempt_count":35,"max_ms":2156476,"mean_ms":402937.5,"min_ms":36579,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":13,"max_ms":2156476,"mean_ms":830597.625,"min_ms":100447,"run_count":8},"medium":{"attempt_count":12,"max_ms":572210,"mean_ms":258473.0,"min_ms":66883,"run_count":8},"none":{"attempt_count":10,"max_ms":286097,"mean_ms":119741.875,"min_ms":36579,"run_count":8}},"codegen_output_tokens":{"attempt_count":35,"output_max":54472,"output_mean":14159.166666666666,"output_min":1979,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":13,"output_max":47250,"output_mean":26393.0,"output_min":7308,"run_count":8},"medium":{"attempt_count":12,"output_max":54472,"output_mean":12951.25,"output_min":5048,"run_count":8},"none":{"attempt_count":10,"output_max":4856,"output_mean":3133.25,"output_min":1979,"run_count":8}},"display_name":"DeepSeek V4 Flash","economics":{"all":28.238179264379653,"highest":29.836237006649156,"medium":28.03161300449639,"none":27.45111681771463},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":35,"finish_reasons":["stop"],"indexed_attempts":35,"output_token_observations":35,"provider_post_attempt_observations":35,"provider_post_attempts":35,"reasoning_token_observations":35,"reconciliation_get_attempt_observations":35,"reconciliation_get_attempts":166,"total_output_tokens":339820,"total_reasoning_output_tokens":258096,"total_visible_output_tokens":81724,"visible_token_observations":35},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":["GB2-04"],"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":7,"evaluated_cells":8,"failed_game_aliases":["GB2-05"],"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}},"id":"deepseek/deepseek-v4-flash","is_recent_addition":false,"last_measured_at":"2026-09-26T06:36:29Z","match_totals_all":{"draws":2886,"losses":3749,"wins":2164},"match_totals_tracks":{"highest":{"draws":722,"losses":707,"wins":435},"medium":{"draws":1616,"losses":2161,"wins":1240},"none":{"draws":548,"losses":881,"wins":489}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":79.1857783379771,"mean":27.505930812778903,"min":8.068562237133875},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":51,"overall_ranking_status":"ranked","per_game":{"GB2-01":18.608236636018955,"GB2-02":14.185247486385501,"GB2-03":18.725696327182185,"GB2-04":15.477258104068593,"GB2-06":79.1857783379771,"GB2-07":40.544950383391644,"GB2-08":22.126491771520136},"per_game_all":{"GB2-01":25.752710141419204,"GB2-02":11.099652925785287,"GB2-03":22.2668565968703,"GB2-06":56.89930502408174,"GB2-07":31.468135094047188,"GB2-08":21.942415804074184},"per_game_match_totals_all":{"GB2-01":{"draws":210,"losses":663,"wins":247},"GB2-02":{"draws":993,"losses":179,"wins":26},"GB2-03":{"draws":356,"losses":304,"wins":171},"GB2-04":{"draws":526,"losses":206,"wins":70},"GB2-05":{"draws":0,"losses":526,"wins":414},"GB2-06":{"draws":38,"losses":664,"wins":642},"GB2-07":{"draws":0,"losses":830,"wins":452},"GB2-08":{"draws":763,"losses":377,"wins":142}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":65,"losses":153,"wins":8},"GB2-02":{"draws":188,"losses":25,"wins":15},"GB2-03":{"draws":104,"losses":98,"wins":40},"GB2-04":{"draws":163,"losses":93,"wins":42},"GB2-06":{"draws":20,"losses":46,"wins":178},"GB2-07":{"draws":0,"losses":208,"wins":134},"GB2-08":{"draws":182,"losses":84,"wins":18}},"medium":{"GB2-01":{"draws":82,"losses":355,"wins":215},"GB2-02":{"draws":557,"losses":93,"wins":8},"GB2-03":{"draws":159,"losses":105,"wins":85},"GB2-04":{"draws":363,"losses":113,"wins":28},"GB2-05":{"draws":0,"losses":419,"wins":269},"GB2-06":{"draws":7,"losses":478,"wins":275},"GB2-07":{"draws":0,"losses":413,"wins":263},"GB2-08":{"draws":448,"losses":185,"wins":97}},"none":{"GB2-01":{"draws":63,"losses":155,"wins":24},"GB2-02":{"draws":248,"losses":61,"wins":3},"GB2-03":{"draws":93,"losses":101,"wins":46},"GB2-05":{"draws":0,"losses":107,"wins":145},"GB2-06":{"draws":11,"losses":140,"wins":189},"GB2-07":{"draws":0,"losses":209,"wins":55},"GB2-08":{"draws":133,"losses":108,"wins":27}}},"per_game_raw_elo_all":{"GB2-01":1256.2637717954956,"GB2-02":1431.7228349515933,"GB2-03":1337.315025920269,"GB2-06":1604.136211888217,"GB2-07":1261.1808586840264,"GB2-08":1310.7221924587732},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1157.765036038415,"GB2-02":1454.9290541975188,"GB2-03":1297.5760145790557,"GB2-04":1429.5732597749864,"GB2-06":1974.872728275993,"GB2-07":1395.720887779316,"GB2-08":1312.3235057268398},"medium":{"GB2-01":1404.7674056690867,"GB2-02":1411.5468949575748,"GB2-03":1400.5872376688508,"GB2-04":1413.196554926179,"GB2-05":1340.2250922703333,"GB2-06":1257.7281989964772,"GB2-07":1293.4852623759248,"GB2-08":1424.160804698994},"none":{"GB2-01":1206.258873678985,"GB2-02":1428.692555699686,"GB2-03":1313.7818255129,"GB2-05":1507.4080298081694,"GB2-06":1579.8077083921808,"GB2-07":1094.3364258968384,"GB2-08":1195.6822669504859}},"per_game_tracks":{"highest":{"GB2-01":18.608236636018955,"GB2-02":14.185247486385501,"GB2-03":18.725696327182185,"GB2-04":15.477258104068593,"GB2-06":79.1857783379771,"GB2-07":40.544950383391644,"GB2-08":22.126491771520136},"medium":{"GB2-01":36.46935775779218,"GB2-02":8.068562237133875,"GB2-03":27.839697739215346,"GB2-04":12.632744353466148,"GB2-05":39.153358726035805,"GB2-06":35.944023810721106,"GB2-07":33.46847529864371,"GB2-08":30.67668411296293},"none":{"GB2-01":22.18053603044648,"GB2-02":11.045149053836493,"GB2-03":20.235175724213374,"GB2-05":49.713792864113344,"GB2-06":55.56811292354701,"GB2-07":20.390979600106228,"GB2-08":13.024071527739482}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":28.856659942849745,"medium":27.1112849767231,"none":26.54984751876387},"reasoning_agg":{"highest":{"max":79.1857783379771,"mean":28.856659942849745,"min":14.185247486385501},"medium":{"max":39.153358726035805,"mean":27.1112849767231,"min":8.068562237133875},"none":{"max":55.56811292354701,"mean":26.54984751876387,"min":11.045149053836493}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":79.1857783379771,"expected_score":24.340886435521725,"reasoning_variance":2.3068124240858765,"reliability_score":99.94208542079416,"uncertainty_avg":0.05791457920584911,"uncertainty_penalty":-3.1650443772571784},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":79.1857783379771,"expected_score":20.128251986665475,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.72840795618427},"medium":{"ceiling_score":39.153358726035805,"expected_score":26.11270532467416,"reliability_score":99.86969219678684,"uncertainty_avg":0.1303078032131605,"uncertainty_penalty":-0.9985796520489387},"none":{"ceiling_score":55.56811292354701,"expected_score":28.548310487632964,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.9984629688690951}}},{"canonical_public_row_identity":"publication-row.v1:overall:poolside-laguna-s-2-1:714c98e791307e1d","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0068074,"mean":0.0034371900000000006,"median":0.00326368,"min":0.00211404,"recorded_attempt_count":35,"run_count":14,"total":0.04917795999999999},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.04917796000000001},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":false,"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},"cost_is_complete":false,"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":25.916140098789953,"none":31.482942144788865},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T06:41:56Z","match_totals_all":{"draws":2935,"losses":3088,"wins":1678},"match_totals_tracks":{"medium":{"draws":1989,"losses":1863,"wins":801},"none":{"draws":946,"losses":1225,"wins":877}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":48.83723547819472,"mean":27.346278006528163,"min":6.878226574921386},"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":52,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":167,"losses":416,"wins":343},"GB2-02":{"draws":948,"losses":117,"wins":13},"GB2-03":{"draws":550,"losses":565,"wins":307},"GB2-04":{"draws":243,"losses":111,"wins":36},"GB2-05":{"draws":0,"losses":749,"wins":516},"GB2-06":{"draws":21,"losses":471,"wins":180},"GB2-07":{"draws":0,"losses":285,"wins":227},"GB2-08":{"draws":1006,"losses":374,"wins":56}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":72,"losses":231,"wins":167},"GB2-02":{"draws":725,"losses":91,"wins":2},"GB2-03":{"draws":316,"losses":337,"wins":169},"GB2-04":{"draws":243,"losses":111,"wins":36},"GB2-05":{"draws":0,"losses":554,"wins":283},"GB2-06":{"draws":14,"losses":307,"wins":107},"GB2-08":{"draws":619,"losses":232,"wins":37}},"none":{"GB2-01":{"draws":95,"losses":185,"wins":176},"GB2-02":{"draws":223,"losses":26,"wins":11},"GB2-03":{"draws":234,"losses":228,"wins":138},"GB2-05":{"draws":0,"losses":195,"wins":233},"GB2-06":{"draws":7,"losses":164,"wins":73},"GB2-07":{"draws":0,"losses":285,"wins":227},"GB2-08":{"draws":387,"losses":142,"wins":19}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1460.9716222824604,"GB2-02":1465.616782974005,"GB2-03":1403.3089688451896,"GB2-04":1370.6089512476249,"GB2-05":1280.1985293001612,"GB2-06":1136.649389540425,"GB2-08":1317.167886278804},"none":{"GB2-01":1502.225075880726,"GB2-02":1423.079549186166,"GB2-03":1351.3685561481475,"GB2-05":1495.6171911207653,"GB2-06":1130.9662679209262,"GB2-07":1454.486936912778,"GB2-08":1308.434345675667}},"per_game_tracks":{"medium":{"GB2-01":41.129139370202886,"GB2-02":16.618170692872393,"GB2-03":29.188202915275117,"GB2-04":6.878226574921386,"GB2-05":35.77656426941633,"GB2-06":28.953456757481547,"GB2-08":22.86922011136003},"none":{"GB2-01":43.53008655884732,"GB2-02":9.957537569922609,"GB2-03":23.818245617087285,"GB2-05":48.83723547819472,"GB2-06":28.233402850389535,"GB2-07":44.212421355475826,"GB2-08":21.79166558360474}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":24.399812070700555,"none":30.29274394235577},"reasoning_agg":{"medium":{"max":41.129139370202886,"mean":24.399812070700555,"min":6.878226574921386},"none":{"max":48.83723547819472,"mean":30.29274394235577,"min":9.957537569922609}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":48.83723547819472,"reasoning_variance":5.892931871655215},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":41.129139370202886,"expected_score":22.517152098028923,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.8826599726716324},"none":{"ceiling_score":48.83723547819472,"expected_score":32.480879304159075,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.1881353618033046}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-5-flash-lite:a4a9549e62c079e1","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.0222516,"mean":0.01697319375,"median":0.015739925000000002,"min":0.012759,"recorded_attempt_count":34,"run_count":16,"total":0.2715711}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":14,"cell_count":8,"cost_basis_counts":{"provider_reported":48},"cost_is_complete":false,"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":0.6081093000000001},"historical-provider-setting-baseline":{"admitted_cell_count":15,"cell_count":8,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.9722945000000002}},"codegen_cost_usd":{"admitted_cell_count":43,"cell_count":24,"cost_basis_counts":{"provider_reported":132},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.0719635,"mean":0.03858281041666666,"median":0.037386975,"min":0.012759,"recorded_attempt_count":132,"run_count":48,"total":1.8519748999999999},"codegen_latency_ms":{"attempt_count":132,"max_ms":115030,"mean_ms":50137.9375,"min_ms":13430,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":50,"max_ms":115030,"mean_ms":74972.3125,"min_ms":38302,"run_count":16},"medium":{"attempt_count":48,"max_ms":75176,"mean_ms":48761.1875,"min_ms":19840,"run_count":16},"none":{"attempt_count":34,"max_ms":54024,"mean_ms":26680.3125,"min_ms":13430,"run_count":16}},"codegen_output_tokens":{"attempt_count":132,"output_max":33866,"output_mean":12598.979166666666,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":50,"output_max":33866,"output_mean":21067.4375,"output_min":11641,"run_count":16},"medium":{"attempt_count":48,"output_max":19346,"output_mean":12054.5625,"output_min":4066,"run_count":16},"none":{"attempt_count":34,"output_max":9270,"output_mean":4674.9375,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"all":27.52414658723603,"highest":29.99964735241055,"medium":22.32588422438232,"none":30.2469081849152},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T06:49:51Z","match_totals_all":{"draws":5193,"losses":7652,"wins":4260},"match_totals_tracks":{"highest":{"draws":1296,"losses":2324,"wins":1504},"medium":{"draws":1898,"losses":2687,"wins":955},"none":{"draws":1999,"losses":2641,"wins":1801}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":54.81452463617791,"mean":26.79013072241389,"min":9.319252407509502},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":53,"overall_ranking_status":"ranked","per_game":{"GB2-01":37.40764745890132,"GB2-02":16.972917445571756,"GB2-03":32.75380750003364,"GB2-04":17.717368410266104,"GB2-05":25.91013750283033,"GB2-06":44.488870118657296,"GB2-07":43.204632613009736,"GB2-08":21.541797770014227},"per_game_all":{"GB2-01":37.4159659286475,"GB2-02":12.528924621317728,"GB2-03":28.73200795380129,"GB2-04":18.30315068296819,"GB2-05":20.300935443913644,"GB2-06":39.0334184321529,"GB2-07":41.87611518931702,"GB2-08":22.002654445769934},"per_game_match_totals_all":{"GB2-01":{"draws":417,"losses":1090,"wins":711},"GB2-02":{"draws":1248,"losses":176,"wins":35},"GB2-03":{"draws":582,"losses":736,"wins":604},"GB2-04":{"draws":1429,"losses":487,"wins":299},"GB2-05":{"draws":0,"losses":1928,"wins":438},"GB2-06":{"draws":56,"losses":1519,"wins":1003},"GB2-07":{"draws":0,"losses":1131,"wins":1082},"GB2-08":{"draws":1461,"losses":585,"wins":88}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":83,"losses":188,"wins":103},"GB2-02":{"draws":275,"losses":52,"wins":31},"GB2-03":{"draws":167,"losses":301,"wins":288},"GB2-04":{"draws":466,"losses":170,"wins":85},"GB2-05":{"draws":0,"losses":573,"wins":185},"GB2-06":{"draws":35,"losses":437,"wins":360},"GB2-07":{"draws":0,"losses":480,"wins":435},"GB2-08":{"draws":270,"losses":123,"wins":17}},"medium":{"GB2-01":{"draws":161,"losses":471,"wins":336},"GB2-02":{"draws":366,"losses":48,"wins":1},"GB2-03":{"draws":304,"losses":258,"wins":146},"GB2-04":{"draws":469,"losses":95,"wins":53},"GB2-05":{"draws":0,"losses":634,"wins":148},"GB2-06":{"draws":10,"losses":664,"wins":124},"GB2-07":{"draws":0,"losses":303,"wins":109},"GB2-08":{"draws":588,"losses":214,"wins":38}},"none":{"GB2-01":{"draws":173,"losses":431,"wins":272},"GB2-02":{"draws":607,"losses":76,"wins":3},"GB2-03":{"draws":111,"losses":177,"wins":170},"GB2-04":{"draws":494,"losses":222,"wins":161},"GB2-05":{"draws":0,"losses":721,"wins":105},"GB2-06":{"draws":11,"losses":418,"wins":519},"GB2-07":{"draws":0,"losses":348,"wins":538},"GB2-08":{"draws":603,"losses":248,"wins":33}}},"per_game_raw_elo_all":{"GB2-01":1410.5361136423198,"GB2-02":1437.4376586968374,"GB2-03":1398.8075508645882,"GB2-04":1445.9041636740374,"GB2-05":1034.7346260119054,"GB2-06":1303.6251203564818,"GB2-07":1413.3845802548594,"GB2-08":1306.4500177990728},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1411.7513404624647,"GB2-02":1469.5050640652562,"GB2-03":1442.1365655722998,"GB2-04":1442.0909089869072,"GB2-05":1124.30999660883,"GB2-06":1394.3009811388013,"GB2-07":1433.0044244039836,"GB2-08":1300.8230354891007},"medium":{"GB2-01":1433.3584370871959,"GB2-02":1427.4753679490505,"GB2-03":1324.927154887786,"GB2-04":1439.5074052443883,"GB2-05":1047.531566403462,"GB2-06":962.6000875142872,"GB2-07":1198.4542261815182,"GB2-08":1310.625723495411},"none":{"GB2-01":1386.498563377299,"GB2-02":1415.3325440762055,"GB2-03":1429.358932133679,"GB2-04":1456.114176790817,"GB2-05":932.3623150234243,"GB2-06":1553.9742924163575,"GB2-07":1608.6950901790765,"GB2-08":1307.9012944127069}},"per_game_tracks":{"highest":{"GB2-01":37.40764745890132,"GB2-02":16.972917445571756,"GB2-03":32.75380750003364,"GB2-04":17.717368410266104,"GB2-05":25.91013750283033,"GB2-06":44.488870118657296,"GB2-07":43.204632613009736,"GB2-08":21.541797770014227},"medium":{"GB2-01":39.14858317690402,"GB2-02":11.294604010871925,"GB2-03":21.705338326621902,"GB2-04":17.02478717210354,"GB2-05":21.101179390543543,"GB2-06":18.403317035942425,"GB2-07":27.609188318763415,"GB2-08":22.32007636330779},"none":{"GB2-01":35.69166715013715,"GB2-02":9.319252407509502,"GB2-03":31.736878034748326,"GB2-04":20.167296466534918,"GB2-05":13.891489438367064,"GB2-06":54.208068141858966,"GB2-07":54.81452463617791,"GB2-08":22.146089203987785}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.01470523447714,"medium":21.592885484951065,"none":29.76280144781346},"reasoning_agg":{"highest":{"max":44.488870118657296,"mean":29.01470523447714,"min":16.972917445571756},"medium":{"max":39.14858317690402,"mean":21.592885484951065,"min":11.294604010871925},"none":{"max":54.81452463617791,"mean":29.76280144781346,"min":9.319252407509502}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":54.81452463617791,"expected_score":22.84460367040073,"reasoning_variance":8.169915962862394,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.9455270520131585},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":44.488870118657296,"expected_score":19.17196555410964,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.842739680367501},"medium":{"ceiling_score":39.14858317690402,"expected_score":18.198634976286925,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.3942505086641397},"none":{"ceiling_score":54.81452463617791,"expected_score":31.16321048080564,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.4004090329921794}}},{"canonical_public_row_identity":"publication-row.v1:overall:tencent-hy3-preview:fcc77a4d882226b3","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.001632522,"mean":0.00126739675,"median":0.001232095,"min":0.00090937,"recorded_attempt_count":11,"run_count":8,"total":0.010139174},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.007539277999999999,"mean":0.0022565913437500003,"median":0.0014932259999999998,"min":0.00090937,"recorded_attempt_count":25,"run_count":17,"total":0.041725612999999995},"codegen_latency_ms":{"attempt_count":25,"max_ms":368409,"mean_ms":82415.5294117647,"min_ms":16892,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":368409,"mean_ms":127998.11111111111,"min_ms":27775,"run_count":9},"none":{"attempt_count":11,"max_ms":46063,"mean_ms":31135.125,"min_ms":16892,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":27553,"output_mean":7690.823529411765,"output_min":1430,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":27553,"output_mean":12332.666666666666,"output_min":2974,"run_count":9},"none":{"attempt_count":11,"output_max":3514,"output_mean":2468.75,"output_min":1430,"run_count":8}},"display_name":"Hy3 Preview","economics":{"highest":32.171799835723974,"none":24.483183628427884},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T02:00:18Z","match_totals_all":{"draws":1075,"losses":1090,"wins":763},"match_totals_tracks":{"highest":{"draws":465,"losses":628,"wins":459},"none":{"draws":610,"losses":462,"wins":304}},"model_slug":"tencent-hy3-preview","overall":{"max":61.48669928023902,"mean":26.4984244696891,"min":3.9015347451152658},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":54,"overall_ranking_status":"partial","per_game":{"GB2-01":56.76015343291601,"GB2-02":5.9882846010899025,"GB2-04":10.489686390255008,"GB2-05":61.48669928023902,"GB2-06":28.465306858036236,"GB2-07":30.32453824116038,"GB2-08":31.687930046371267},"per_game_match_totals_all":{"GB2-01":{"draws":72,"losses":98,"wins":238},"GB2-02":{"draws":339,"losses":77,"wins":2},"GB2-03":{"draws":62,"losses":100,"wins":42},"GB2-04":{"draws":316,"losses":77,"wins":51},"GB2-05":{"draws":0,"losses":246,"wins":186},"GB2-06":{"draws":0,"losses":158,"wins":50},"GB2-07":{"draws":0,"losses":165,"wins":91},"GB2-08":{"draws":286,"losses":169,"wins":103}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":36,"losses":62,"wins":106},"GB2-02":{"draws":165,"losses":37,"wins":2},"GB2-04":{"draws":184,"losses":48,"wins":8},"GB2-05":{"draws":0,"losses":63,"wins":113},"GB2-06":{"draws":0,"losses":158,"wins":50},"GB2-07":{"draws":0,"losses":165,"wins":91},"GB2-08":{"draws":80,"losses":95,"wins":89}},"none":{"GB2-01":{"draws":36,"losses":36,"wins":132},"GB2-02":{"draws":174,"losses":40,"wins":0},"GB2-03":{"draws":62,"losses":100,"wins":42},"GB2-04":{"draws":132,"losses":29,"wins":43},"GB2-05":{"draws":0,"losses":183,"wins":73},"GB2-08":{"draws":206,"losses":74,"wins":14}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1686.5578444656303,"GB2-02":1397.9260322087162,"GB2-04":1399.6909208556438,"GB2-05":1699.5118500851947,"GB2-06":1136.9207292360672,"GB2-07":1244.7291028360266,"GB2-08":1436.4540900302532},"none":{"GB2-01":1668.9099632612854,"GB2-02":1382.373992428729,"GB2-03":1291.6821137938018,"GB2-04":1457.4383395327309,"GB2-05":1099.7712464212616,"GB2-08":1367.6750288878484}},"per_game_tracks":{"highest":{"GB2-01":56.76015343291601,"GB2-02":5.9882846010899025,"GB2-04":10.489686390255008,"GB2-05":61.48669928023902,"GB2-06":28.465306858036236,"GB2-07":30.32453824116038,"GB2-08":31.687930046371267},"none":{"GB2-01":55.48352333542866,"GB2-02":3.9015347451152658,"GB2-03":17.959581617290976,"GB2-04":19.014461335684,"GB2-05":24.088143861407563,"GB2-08":26.451856875640857}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":30.21267928847423,"none":22.784169650903962},"reasoning_agg":{"highest":{"max":61.48669928023902,"mean":30.21267928847423,"min":5.9882846010899025},"none":{"max":55.48352333542866,"mean":22.784169650903962,"min":3.9015347451152658}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":61.48669928023902,"reasoning_variance":7.428509637570269},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":61.48669928023902,"expected_score":23.293154017218324,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.919525271255907},"none":{"ceiling_score":55.48352333542866,"expected_score":26.245533792230876,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.4613641413269143}}},{"canonical_public_row_identity":"publication-row.v1:overall:x-ai-grok-build-0-1:32d67c2437a4ce5d","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","max":0.07439860000000001,"mean":0.060660574999999994,"median":0.0565846,"min":0.0485456,"recorded_attempt_count":17,"run_count":8,"total":0.4852846}},"codegen_cost_usd":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"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":26.316180112731868},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T05:00:58Z","match_totals_all":{"draws":721,"losses":757,"wins":434},"match_totals_tracks":{"medium":{"draws":721,"losses":757,"wins":434}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":52.62593790637412,"mean":26.316180112731868,"min":12.332158914063934},"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":55,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":51,"losses":93,"wins":74},"GB2-02":{"draws":220,"losses":34,"wins":6},"GB2-03":{"draws":60,"losses":67,"wins":31},"GB2-04":{"draws":198,"losses":34,"wins":10},"GB2-05":{"draws":0,"losses":97,"wins":137},"GB2-06":{"draws":0,"losses":154,"wins":108},"GB2-07":{"draws":0,"losses":209,"wins":57},"GB2-08":{"draws":192,"losses":69,"wins":11}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":51,"losses":93,"wins":74},"GB2-02":{"draws":220,"losses":34,"wins":6},"GB2-03":{"draws":60,"losses":67,"wins":31},"GB2-04":{"draws":198,"losses":34,"wins":10},"GB2-05":{"draws":0,"losses":97,"wins":137},"GB2-06":{"draws":0,"losses":154,"wins":108},"GB2-07":{"draws":0,"losses":209,"wins":57},"GB2-08":{"draws":192,"losses":69,"wins":11}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1360.3436374608693,"GB2-02":1440.0288920121197,"GB2-03":1290.0275676841704,"GB2-04":1439.023168839354,"GB2-05":1554.6556213874103,"GB2-06":1381.7196621240264,"GB2-07":980.3078339566572,"GB2-08":1312.2610560425574}},"per_game_tracks":{"medium":{"GB2-01":33.22780687930118,"GB2-02":12.332158914063934,"GB2-03":17.44958880553022,"GB2-04":16.53908705114465,"GB2-05":52.62593790637412,"GB2-06":43.42682725993031,"GB2-07":12.846349817632971,"GB2-08":22.081684267877538}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.316180112731868},"reasoning_agg":{"medium":{"max":52.62593790637412,"mean":26.316180112731868,"min":12.332158914063934}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":52.62593790637412},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":52.62593790637412,"expected_score":24.15781013876345,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.1583699739684192}}},{"canonical_public_row_identity":"publication-row.v1:overall:qwen-qwen3-7-plus:6637b5994cf7a3b7","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.08827968,"mean":0.05437612,"median":0.0574344,"min":0.00733824,"recorded_attempt_count":16,"run_count":8,"total":0.43500895999999994},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":16},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0154064,"mean":0.00874386,"median":0.0064215999999999995,"min":0.00524064,"recorded_attempt_count":13,"run_count":9,"total":0.08145696}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":29},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":5,"max":0.08827968,"mean":0.03155999,"median":0.01479536,"min":0.00524064,"recorded_attempt_count":29,"run_count":17,"total":0.5164659199999999},"codegen_latency_ms":{"attempt_count":29,"max_ms":1361767,"mean_ms":422352.64705882355,"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":36.935077048729106,"none":19.363839493349296},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T05:35:58Z","match_totals_all":{"draws":925,"losses":1152,"wins":680},"match_totals_tracks":{"medium":{"draws":479,"losses":494,"wins":459},"none":{"draws":446,"losses":658,"wins":221}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":71.58697427396798,"mean":25.934583168313804,"min":9.022662777519397},"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":56,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":92,"losses":204,"wins":100},"GB2-02":{"draws":421,"losses":31,"wins":6},"GB2-04":{"draws":174,"losses":24,"wins":17},"GB2-05":{"draws":0,"losses":217,"wins":211},"GB2-06":{"draws":7,"losses":226,"wins":217},"GB2-07":{"draws":0,"losses":397,"wins":129},"GB2-08":{"draws":231,"losses":53,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":43,"losses":84,"wins":71},"GB2-02":{"draws":201,"losses":13,"wins":6},"GB2-05":{"draws":0,"losses":105,"wins":121},"GB2-06":{"draws":4,"losses":50,"wins":170},"GB2-07":{"draws":0,"losses":189,"wins":91},"GB2-08":{"draws":231,"losses":53,"wins":0}},"none":{"GB2-01":{"draws":49,"losses":120,"wins":29},"GB2-02":{"draws":220,"losses":18,"wins":0},"GB2-04":{"draws":174,"losses":24,"wins":17},"GB2-05":{"draws":0,"losses":112,"wins":90},"GB2-06":{"draws":3,"losses":176,"wins":47},"GB2-07":{"draws":0,"losses":208,"wins":38}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1454.7449960896188,"GB2-02":1430.1719364461994,"GB2-05":1558.2841070860504,"GB2-06":1850.1279855242137,"GB2-07":1149.751351174684,"GB2-08":1316.873284515054},"none":{"GB2-01":1183.2239510000604,"GB2-02":1417.5211608786092,"GB2-04":1434.692667459592,"GB2-05":1374.1913771656175,"GB2-06":958.2330149532941,"GB2-07":973.1734223860599}},"per_game_tracks":{"medium":{"GB2-01":39.960803210674634,"GB2-02":10.650316976868547,"GB2-05":52.825480963201954,"GB2-06":71.58697427396798,"GB2-07":24.1074420428939,"GB2-08":22.479444824767643},"none":{"GB2-01":20.31924203690549,"GB2-02":9.022662777519397,"GB2-04":15.636084262501875,"GB2-05":41.15115938110248,"GB2-06":17.744314295277277,"GB2-07":12.309574206789252}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":34.37196217285774,"none":17.497204163769865},"reasoning_agg":{"medium":{"max":71.58697427396798,"mean":34.37196217285774,"min":10.650316976868547},"none":{"max":41.15115938110248,"mean":17.497204163769865,"min":9.022662777519397}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":71.58697427396798,"reasoning_variance":16.874758009087877},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":71.58697427396798,"expected_score":37.67592505119662,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.3039628783388792},"none":{"ceiling_score":41.15115938110248,"expected_score":18.266402100688918,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.7691979369190527}}},{"canonical_public_row_identity":"publication-row.v1:overall:meituan-longcat-2-0:c666de4f0835c2f6","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.21404720400000005}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":70},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":1.6004064600000003},"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":26.235538986757966,"none":26.69115665211859},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T06:22:34Z","match_totals_all":{"draws":2318,"losses":3764,"wins":1972},"match_totals_tracks":{"medium":{"draws":1262,"losses":2377,"wins":1186},"none":{"draws":1056,"losses":1387,"wins":786}},"model_slug":"meituan-longcat-2-0","overall":{"max":42.15448920700949,"mean":25.114879133935435,"min":7.232428617079738},"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":57,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":157,"losses":180,"wins":147},"GB2-02":{"draws":543,"losses":73,"wins":2},"GB2-03":{"draws":290,"losses":249,"wins":154},"GB2-04":{"draws":547,"losses":271,"wins":110},"GB2-05":{"draws":0,"losses":847,"wins":415},"GB2-06":{"draws":84,"losses":808,"wins":418},"GB2-07":{"draws":0,"losses":837,"wins":545},"GB2-08":{"draws":697,"losses":499,"wins":181}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":324,"losses":44,"wins":2},"GB2-03":{"draws":165,"losses":131,"wins":87},"GB2-04":{"draws":425,"losses":222,"wins":66},"GB2-05":{"draws":0,"losses":513,"wins":325},"GB2-06":{"draws":48,"losses":550,"wins":224},"GB2-07":{"draws":0,"losses":531,"wins":327},"GB2-08":{"draws":300,"losses":386,"wins":155}},"none":{"GB2-01":{"draws":157,"losses":180,"wins":147},"GB2-02":{"draws":219,"losses":29,"wins":0},"GB2-03":{"draws":125,"losses":118,"wins":67},"GB2-04":{"draws":122,"losses":49,"wins":44},"GB2-05":{"draws":0,"losses":334,"wins":90},"GB2-06":{"draws":36,"losses":258,"wins":194},"GB2-07":{"draws":0,"losses":306,"wins":218},"GB2-08":{"draws":397,"losses":113,"wins":26}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1433.4182855284507,"GB2-03":1385.5397719370314,"GB2-04":1420.2120226957823,"GB2-05":1276.2895116209238,"GB2-06":1189.7314409220562,"GB2-07":1346.932617223217,"GB2-08":1341.8670396835214},"none":{"GB2-01":1410.8936316635102,"GB2-02":1404.2181213636352,"GB2-03":1390.6274611910717,"GB2-04":1493.6712331027038,"GB2-05":1021.1027575423295,"GB2-06":1361.5421257824128,"GB2-07":1301.7112063296167,"GB2-08":1318.1065659851638}},"per_game_tracks":{"medium":{"GB2-02":11.96534718459995,"GB2-03":27.46510526131099,"GB2-04":14.342337487858114,"GB2-05":35.53046663664543,"GB2-06":32.13443974882757,"GB2-07":37.46620442470752,"GB2-08":24.744872163356213},"none":{"GB2-01":36.98356285394554,"GB2-02":7.232428617079738,"GB2-03":26.85286145432655,"GB2-04":24.682700240487225,"GB2-05":18.98586604486369,"GB2-06":42.15448920700949,"GB2-07":34.11672952823746,"GB2-08":22.520615270999055}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":24.414920062239542,"none":25.814838205631332},"reasoning_agg":{"medium":{"max":37.46620442470752,"mean":24.414920062239542,"min":11.96534718459995},"none":{"max":42.15448920700949,"mean":25.814838205631332,"min":7.232428617079738}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":42.15448920700949,"reasoning_variance":1.3999181433917904},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":37.46620442470752,"expected_score":23.41277244265685,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0021476195826935},"none":{"ceiling_score":42.15448920700949,"expected_score":27.835474252475063,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.0206360468437303}}},{"canonical_public_row_identity":"publication-row.v1:overall:openai-gpt-oss-120b:64abe68ef22a237c","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.015120192000000001,"mean":0.0074424702499999995,"median":0.006876,"min":0.00134592,"recorded_attempt_count":11,"run_count":8,"total":0.059539762},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085673000000002},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855891}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.00145295,"mean":0.001135709125,"median":0.001180259,"min":0.00078534,"recorded_attempt_count":10,"run_count":8,"total":0.009085673},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.002555,"mean":0.001231986375,"median":0.0010393855,"min":0.00046744,"recorded_attempt_count":12,"run_count":8,"total":0.009855890999999999},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.015120192000000001,"mean":0.0074424702499999995,"median":0.006876,"min":0.00134592,"recorded_attempt_count":11,"run_count":8,"total":0.059539762}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":33},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.015120192000000001,"mean":0.0032700552500000003,"median":0.0013951725,"min":0.00046744,"recorded_attempt_count":33,"run_count":24,"total":0.078481326},"codegen_latency_ms":{"attempt_count":33,"max_ms":1105859,"mean_ms":161415.45833333334,"min_ms":22661,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":1105859,"mean_ms":300420.375,"min_ms":56038,"run_count":8},"medium":{"attempt_count":10,"max_ms":291211,"mean_ms":111417.625,"min_ms":22661,"run_count":8},"none":{"attempt_count":12,"max_ms":151123,"mean_ms":72408.375,"min_ms":26216,"run_count":8}},"codegen_output_tokens":{"attempt_count":33,"output_max":63626,"output_mean":9305.125,"output_min":1487,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":63626,"output_mean":22255.875,"output_min":2344,"run_count":8},"medium":{"attempt_count":10,"output_max":5420,"output_mean":3175.75,"output_min":2107,"run_count":8},"none":{"attempt_count":12,"output_max":4178,"output_mean":2483.75,"output_min":1487,"run_count":8}},"display_name":"GPT-OSS 120B","economics":{"all":24.552475392063037,"highest":27.100552340792518,"medium":23.300275417789653,"none":26.327300209719244},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":33,"finish_reasons":["stop"],"indexed_attempts":33,"output_token_observations":33,"provider_post_attempt_observations":33,"provider_post_attempts":33,"reasoning_token_observations":33,"reconciliation_get_attempt_observations":33,"reconciliation_get_attempts":158,"total_output_tokens":223323,"total_reasoning_output_tokens":139050,"total_visible_output_tokens":87482,"visible_token_observations":33},"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":"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-04","GB2-06"],"first_pass_admitted":5,"first_pass_rate":0.625,"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":1,"repaired_rate":0.125},"intensive":{"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}},"id":"openai/gpt-oss-120b","is_recent_addition":false,"last_measured_at":"2026-09-26T06:45:30Z","match_totals_all":{"draws":1955,"losses":2383,"wins":1101},"match_totals_tracks":{"highest":{"draws":648,"losses":715,"wins":412},"medium":{"draws":766,"losses":971,"wins":365},"none":{"draws":541,"losses":697,"wins":324}},"model_slug":"openai-gpt-oss-120b","overall":{"max":52.32425830480758,"mean":24.670460540358903,"min":6.343928822258831},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":58,"overall_ranking_status":"ranked","per_game":{"GB2-02":10.587463230489611,"GB2-03":29.0493640135724,"GB2-04":17.797719422094115,"GB2-05":52.32425830480758,"GB2-06":26.86162719505602,"GB2-07":35.310171841015375,"GB2-08":17.77326237851253},"per_game_all":{"GB2-02":10.664342680872767,"GB2-03":27.922723754502073,"GB2-05":32.00198005461279,"GB2-07":32.0182577675615,"GB2-08":20.15507270276606},"per_game_match_totals_all":{"GB2-01":{"draws":96,"losses":292,"wins":198},"GB2-02":{"draws":636,"losses":71,"wins":9},"GB2-03":{"draws":269,"losses":267,"wins":181},"GB2-04":{"draws":372,"losses":139,"wins":53},"GB2-05":{"draws":0,"losses":511,"wins":223},"GB2-06":{"draws":3,"losses":338,"wins":147},"GB2-07":{"draws":0,"losses":522,"wins":268},"GB2-08":{"draws":579,"losses":243,"wins":22}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":199,"losses":38,"wins":7},"GB2-03":{"draws":95,"losses":77,"wins":69},"GB2-04":{"draws":162,"losses":42,"wins":36},"GB2-05":{"draws":0,"losses":126,"wins":126},"GB2-06":{"draws":0,"losses":183,"wins":65},"GB2-07":{"draws":0,"losses":153,"wins":105},"GB2-08":{"draws":192,"losses":96,"wins":4}},"medium":{"GB2-01":{"draws":48,"losses":134,"wins":76},"GB2-02":{"draws":213,"losses":19,"wins":2},"GB2-03":{"draws":101,"losses":88,"wins":53},"GB2-04":{"draws":210,"losses":97,"wins":17},"GB2-05":{"draws":0,"losses":204,"wins":48},"GB2-06":{"draws":3,"losses":155,"wins":82},"GB2-07":{"draws":0,"losses":197,"wins":71},"GB2-08":{"draws":191,"losses":77,"wins":16}},"none":{"GB2-01":{"draws":48,"losses":158,"wins":122},"GB2-02":{"draws":224,"losses":14,"wins":0},"GB2-03":{"draws":73,"losses":102,"wins":59},"GB2-05":{"draws":0,"losses":181,"wins":49},"GB2-07":{"draws":0,"losses":172,"wins":92},"GB2-08":{"draws":196,"losses":70,"wins":2}}},"per_game_raw_elo_all":{"GB2-02":1429.205814206832,"GB2-03":1395.8301859514388,"GB2-05":1226.1854884022966,"GB2-07":1269.9607634839383,"GB2-08":1287.033642256605},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1428.3714558875322,"GB2-03":1407.73745850232,"GB2-04":1447.334957801527,"GB2-05":1548.9136657017382,"GB2-06":1108.0399326326,"GB2-07":1319.9238933950387,"GB2-08":1255.8820346753157},"medium":{"GB2-01":1345.1921901018554,"GB2-02":1430.6210617940046,"GB2-03":1363.9441297771823,"GB2-04":1369.0847854387455,"GB2-05":1078.4370827360356,"GB2-06":1291.4580599696199,"GB2-07":1194.4953362527822,"GB2-08":1340.5162881303563},"none":{"GB2-01":1512.293861790469,"GB2-02":1428.6249249389598,"GB2-03":1415.808969574814,"GB2-05":1051.2057167691164,"GB2-07":1295.4630608039943,"GB2-08":1264.702603964142}},"per_game_tracks":{"highest":{"GB2-02":10.587463230489611,"GB2-03":29.0493640135724,"GB2-04":17.797719422094115,"GB2-05":52.32425830480758,"GB2-06":26.86162719505602,"GB2-07":35.310171841015375,"GB2-08":17.77326237851253},"medium":{"GB2-01":32.289082263323685,"GB2-02":10.827252626324086,"GB2-03":24.948308370060417,"GB2-04":6.343928822258831,"GB2-05":22.733991006236113,"GB2-06":37.91063269510594,"GB2-07":27.03543613107913,"GB2-08":24.313571427929027},"none":{"GB2-01":44.57974970739618,"GB2-02":10.578312185804606,"GB2-03":29.770498879873394,"GB2-05":20.94769085279466,"GB2-07":33.70916533059,"GB2-08":18.378384301856617}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":26.210792701082603,"medium":23.300275417789653,"none":24.500313502204452},"reasoning_agg":{"highest":{"max":52.32425830480758,"mean":26.210792701082603,"min":10.587463230489611},"medium":{"max":37.91063269510594,"mean":23.300275417789653,"min":6.343928822258831},"none":{"max":44.57974970739618,"mean":24.500313502204452,"min":10.578312185804606}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":52.32425830480758,"expected_score":21.119427693768383,"reasoning_variance":2.9105172832929505,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.5510328465905197},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":52.32425830480758,"expected_score":15.621259474909504,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.5895332261731},"medium":{"ceiling_score":37.91063269510594,"expected_score":20.63443302174943,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.6658423960402224},"none":{"ceiling_score":44.57974970739618,"expected_score":28.302865592705288,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.8025520905008356}}},{"canonical_public_row_identity":"publication-row.v1:overall:stepfun-step-3-7-flash:a38a5f6eb512ab7e","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"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":0.48605809999999994},"medium":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"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},"none":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.03772852,"mean":0.024905897500000003,"median":0.026095300000000002,"min":0.00984735,"recorded_attempt_count":20,"run_count":8,"total":0.19924718000000002}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":4,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.03772852,"mean":0.024905897500000003,"median":0.026095300000000002,"min":0.00984735,"recorded_attempt_count":20,"run_count":8,"total":0.19924718},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.11219570000000001,"mean":0.0607572625,"median":0.060057275,"min":0.02174195,"recorded_attempt_count":20,"run_count":8,"total":0.48605810000000005}},"codegen_cost_usd":{"admitted_cell_count":13,"cell_count":24,"cost_basis_counts":{"provider_reported":59},"cost_is_complete":false,"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":1.00006698},"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":38.063355350249296,"highest":27.610343454786282,"medium":25.208583158846768,"none":33.4129710248965},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T05:33:24Z","match_totals_all":{"draws":947,"losses":1892,"wins":988},"match_totals_tracks":{"highest":{"draws":222,"losses":622,"wins":285},"medium":{"draws":404,"losses":378,"wins":186},"none":{"draws":321,"losses":892,"wins":517}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":48.82124208360265,"mean":24.614702468195265,"min":9.823846871751254},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":59,"overall_ranking_status":"partial","per_game":{"GB2-01":9.823846871751254,"GB2-05":42.95353174754254,"GB2-06":33.789497189460036,"GB2-07":25.81550867273385,"GB2-08":25.669332792443715},"per_game_all":{"GB2-05":43.20768189013318,"GB2-06":32.91902881036541},"per_game_match_totals_all":{"GB2-01":{"draws":15,"losses":145,"wins":18},"GB2-02":{"draws":205,"losses":28,"wins":5},"GB2-04":{"draws":195,"losses":32,"wins":23},"GB2-05":{"draws":0,"losses":449,"wins":365},"GB2-06":{"draws":44,"losses":625,"wins":331},"GB2-07":{"draws":0,"losses":431,"wins":242},"GB2-08":{"draws":488,"losses":182,"wins":4}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":145,"wins":18},"GB2-05":{"draws":0,"losses":93,"wins":105},"GB2-06":{"draws":8,"losses":163,"wins":75},"GB2-07":{"draws":0,"losses":164,"wins":83},"GB2-08":{"draws":199,"losses":57,"wins":4}},"medium":{"GB2-02":{"draws":205,"losses":28,"wins":5},"GB2-04":{"draws":195,"losses":32,"wins":23},"GB2-05":{"draws":0,"losses":118,"wins":108},"GB2-06":{"draws":4,"losses":200,"wins":50}},"none":{"GB2-05":{"draws":0,"losses":238,"wins":152},"GB2-06":{"draws":32,"losses":262,"wins":206},"GB2-07":{"draws":0,"losses":267,"wins":159},"GB2-08":{"draws":289,"losses":125,"wins":0}}},"per_game_raw_elo_all":{"GB2-05":1403.859336497371,"GB2-06":1205.8079452593404},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1039.6798458679411,"GB2-05":1403.129321818116,"GB2-06":1222.8862524843107,"GB2-07":1177.0840086456608,"GB2-08":1359.0582971860765},"medium":{"GB2-02":1428.2342361734054,"GB2-04":1451.5575754104434,"GB2-05":1494.6178817544785,"GB2-06":1043.1942507109195},"none":{"GB2-05":1313.830805919518,"GB2-06":1351.343332582791,"GB2-07":1296.6579090921236,"GB2-08":1276.5606004218434}},"per_game_tracks":{"highest":{"GB2-01":9.823846871751254,"GB2-05":42.95353174754254,"GB2-06":33.789497189460036,"GB2-07":25.81550867273385,"GB2-08":25.669332792443715},"medium":{"GB2-02":10.523576265295578,"GB2-04":18.524949216847347,"GB2-05":48.82124208360265,"GB2-06":22.9645650696415},"none":{"GB2-05":37.84827183925436,"GB2-06":42.00302417199472,"GB2-07":34.13357554120723,"GB2-08":19.667012547129705}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":24.54945263487469,"medium":21.197807211899406,"none":28.0968475578117},"reasoning_agg":{"highest":{"max":42.95353174754254,"mean":24.54945263487469,"min":9.823846871751254},"medium":{"max":48.82124208360265,"mean":21.197807211899406,"min":10.523576265295578},"none":{"max":42.00302417199472,"mean":28.0968475578117,"min":19.667012547129705}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low"},"score_diagnostics":{"ceiling_score":48.82124208360265,"expected_score":30.8299041536515,"reasoning_variance":6.899040345912294,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.215201685456236},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":42.95353174754254,"expected_score":15.960079082155648,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.589373552719042},"medium":{"ceiling_score":48.82124208360265,"expected_score":21.525396342675585,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.3275891307761789},"none":{"ceiling_score":42.00302417199472,"expected_score":31.493529354548922,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.396681796737223}}},{"canonical_public_row_identity":"publication-row.v1:overall:meta-muse-glimmer-30b:0d57fdf1ac4ff397","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0138593,"mean":0.00832475125,"median":0.006849235,"min":0.00556902,"recorded_attempt_count":10,"run_count":8,"total":0.06659801},"none":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.058501660000000004}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":10},"cost_is_complete":true,"evidence_basis":"Provider-reported","max":0.0138593,"mean":0.00832475125,"median":0.006849235,"min":0.00556902,"recorded_attempt_count":10,"run_count":8,"total":0.06659801},"historical-provider-setting-baseline":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":13},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.01024177,"mean":0.0073127075,"median":0.007628165,"min":0.00402612,"recorded_attempt_count":13,"run_count":8,"total":0.058501660000000004},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":1,"max":0.02351982,"mean":0.019656965,"median":0.019640945,"min":0.01650772,"recorded_attempt_count":11,"run_count":8,"total":0.15725572}},"codegen_cost_usd":{"admitted_cell_count":21,"cell_count":24,"cost_basis_counts":{"provider_reported":34},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.02351982,"mean":0.011764807916666668,"median":0.0084872,"min":0.00402612,"recorded_attempt_count":34,"run_count":24,"total":0.28235539},"codegen_latency_ms":{"attempt_count":34,"max_ms":380009,"mean_ms":93239.75,"min_ms":17041,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":380009,"mean_ms":168796.875,"min_ms":74942,"run_count":8},"medium":{"attempt_count":10,"max_ms":111336,"mean_ms":66228.375,"min_ms":28934,"run_count":8},"none":{"attempt_count":13,"max_ms":72200,"mean_ms":44694.0,"min_ms":17041,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":16539,"output_mean":6423.083333333333,"output_min":1715,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":16539,"output_mean":12718.0,"output_min":9279,"run_count":8},"medium":{"attempt_count":10,"output_max":6754,"output_mean":3630.75,"output_min":2165,"run_count":8},"none":{"attempt_count":13,"output_max":4210,"output_mean":2920.5,"output_min":1715,"run_count":8}},"display_name":"Muse Glimmer 30B","economics":{"all":26.265714189535178,"highest":30.9253072277398,"medium":21.135626575858865,"none":22.78618060014006},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":34,"finish_reasons":["stop"],"indexed_attempts":34,"output_token_observations":34,"provider_post_attempt_observations":34,"provider_post_attempts":34,"reasoning_token_observations":34,"reconciliation_get_attempt_observations":34,"reconciliation_get_attempts":164,"total_output_tokens":154154,"total_reasoning_output_tokens":105962,"total_visible_output_tokens":48432,"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":"other","provider_model":"meta/muse-glimmer-30b","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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},"baseline":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-02","GB2-06"],"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},"intensive":{"admitted_plugins":7,"evaluated_cells":8,"failed_game_aliases":["GB2-06"],"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}},"id":"meta/muse-glimmer-30b","is_recent_addition":false,"last_measured_at":"2026-09-26T06:38:33Z","match_totals_all":{"draws":2152,"losses":2271,"wins":1115},"match_totals_tracks":{"highest":{"draws":790,"losses":668,"wins":480},"medium":{"draws":784,"losses":887,"wins":341},"none":{"draws":578,"losses":716,"wins":294}},"model_slug":"meta-muse-glimmer-30b","overall":{"max":48.9036611917772,"mean":24.083510334006416,"min":6.212744302293263},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":60,"overall_ranking_status":"ranked","per_game":{"GB2-01":30.606892923975515,"GB2-02":16.78688494377576,"GB2-03":28.624606567170858,"GB2-04":23.245705745467834,"GB2-05":48.9036611917772,"GB2-07":44.191033889033655,"GB2-08":24.118365332977753},"per_game_all":{"GB2-01":28.16135224741558,"GB2-03":27.01713953808121,"GB2-04":18.783238765833516,"GB2-05":24.82460185960645,"GB2-07":35.89028880358193,"GB2-08":22.917663922692373},"per_game_match_totals_all":{"GB2-01":{"draws":217,"losses":373,"wins":158},"GB2-02":{"draws":471,"losses":29,"wins":2},"GB2-03":{"draws":304,"losses":260,"wins":174},"GB2-04":{"draws":571,"losses":189,"wins":102},"GB2-05":{"draws":0,"losses":575,"wins":203},"GB2-06":{"draws":2,"losses":201,"wins":57},"GB2-07":{"draws":0,"losses":473,"wins":377},"GB2-08":{"draws":587,"losses":171,"wins":42}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":75,"losses":114,"wins":41},"GB2-02":{"draws":237,"losses":14,"wins":1},"GB2-03":{"draws":114,"losses":77,"wins":47},"GB2-04":{"draws":173,"losses":74,"wins":61},"GB2-05":{"draws":0,"losses":177,"wins":141},"GB2-07":{"draws":0,"losses":154,"wins":170},"GB2-08":{"draws":191,"losses":58,"wins":19}},"medium":{"GB2-01":{"draws":71,"losses":142,"wins":31},"GB2-02":{"draws":234,"losses":15,"wins":1},"GB2-03":{"draws":85,"losses":107,"wins":62},"GB2-04":{"draws":191,"losses":41,"wins":20},"GB2-05":{"draws":0,"losses":183,"wins":43},"GB2-06":{"draws":2,"losses":201,"wins":57},"GB2-07":{"draws":0,"losses":142,"wins":116},"GB2-08":{"draws":201,"losses":56,"wins":11}},"none":{"GB2-01":{"draws":71,"losses":117,"wins":86},"GB2-03":{"draws":105,"losses":76,"wins":65},"GB2-04":{"draws":207,"losses":74,"wins":21},"GB2-05":{"draws":0,"losses":215,"wins":19},"GB2-07":{"draws":0,"losses":177,"wins":91},"GB2-08":{"draws":195,"losses":57,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1288.6078245867718,"GB2-03":1385.8075884753198,"GB2-04":1451.6211568396768,"GB2-05":1111.5419836944975,"GB2-07":1327.6402381355867,"GB2-08":1323.2777943706808},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1323.4012155529406,"GB2-02":1472.2138112256239,"GB2-03":1403.368025411251,"GB2-04":1479.8415343304644,"GB2-05":1491.7750894078754,"GB2-07":1451.3728178736649,"GB2-08":1338.6944385717682},"medium":{"GB2-01":1181.3639638123595,"GB2-02":1409.1053012460525,"GB2-03":1329.742774384414,"GB2-04":1451.5534624604563,"GB2-05":1026.1514240239228,"GB2-06":1072.9432821698413,"GB2-07":1292.2479093090562,"GB2-08":1321.8901389907062},"none":{"GB2-01":1361.0582943950153,"GB2-03":1424.3119656302945,"GB2-04":1423.4684737281098,"GB2-05":816.699437651694,"GB2-07":1239.2999872240396,"GB2-08":1309.248805549568}},"per_game_tracks":{"highest":{"GB2-01":30.606892923975515,"GB2-02":16.78688494377576,"GB2-03":28.624606567170858,"GB2-04":23.245705745467834,"GB2-05":48.9036611917772,"GB2-07":44.191033889033655,"GB2-08":24.118365332977753},"medium":{"GB2-01":20.387255050891774,"GB2-02":7.931305203089884,"GB2-03":21.7989120301416,"GB2-04":18.539655868084658,"GB2-05":19.35740008474889,"GB2-06":24.778201243391056,"GB2-07":33.47752597339482,"GB2-08":22.814757153128255},"none":{"GB2-01":33.48990876737945,"GB2-03":30.627900016931164,"GB2-04":14.56435468394805,"GB2-05":6.212744302293263,"GB2-07":30.002306548317318,"GB2-08":21.819869281971116}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.909974039292045,"medium":21.135626575858865,"none":21.204930386868334},"reasoning_agg":{"highest":{"max":48.9036611917772,"mean":29.909974039292045,"min":16.78688494377576},"medium":{"max":33.47752597339482,"mean":21.135626575858865,"min":7.931305203089884},"none":{"max":33.48990876737945,"mean":21.204930386868334,"min":6.212744302293263}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":48.9036611917772,"expected_score":22.798691085083522,"reasoning_variance":8.77434746343318,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.2848192489228936},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":48.9036611917772,"expected_score":21.596046015006177,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.313928024285868},"medium":{"ceiling_score":33.47752597339482,"expected_score":17.647312340420072,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.488314235438793},"none":{"ceiling_score":33.48990876737945,"expected_score":23.09809466979803,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.8931642829296962}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemma-4-31b-it:055141364decf1b9","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":4,"cell_count":7,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":30.501217841651915,"none":22.04126269064722},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T06:01:35Z","match_totals_all":{"draws":579,"losses":1196,"wins":603},"match_totals_tracks":{"medium":{"draws":185,"losses":486,"wins":303},"none":{"draws":394,"losses":710,"wins":300}},"model_slug":"google-gemma-4-31b-it","overall":{"max":50.72174167918636,"mean":23.86351744242727,"min":13.62340547927469},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality","generation_incomplete"],"overall_official_rank":61,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":49,"losses":77,"wins":104},"GB2-04":{"draws":351,"losses":58,"wins":41},"GB2-05":{"draws":0,"losses":280,"wins":174},"GB2-06":{"draws":3,"losses":342,"wins":129},"GB2-07":{"draws":0,"losses":361,"wins":141},"GB2-08":{"draws":176,"losses":78,"wins":14}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":185,"losses":24,"wins":15},"GB2-05":{"draws":0,"losses":110,"wins":130},"GB2-06":{"draws":0,"losses":183,"wins":61},"GB2-07":{"draws":0,"losses":169,"wins":97}},"none":{"GB2-01":{"draws":49,"losses":77,"wins":104},"GB2-04":{"draws":166,"losses":34,"wins":26},"GB2-05":{"draws":0,"losses":170,"wins":44},"GB2-06":{"draws":3,"losses":159,"wins":68},"GB2-07":{"draws":0,"losses":192,"wins":44},"GB2-08":{"draws":176,"losses":78,"wins":14}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1456.7848554488737,"GB2-05":1524.0526012540347,"GB2-06":1034.5356353380987,"GB2-07":1235.7740492395756},"none":{"GB2-01":1471.2935528834146,"GB2-04":1422.1336343692708,"GB2-05":976.721169780506,"GB2-06":1092.9576246984773,"GB2-07":993.545849463881,"GB2-08":1303.8046711410816}},"per_game_tracks":{"medium":{"GB2-04":19.10911122360846,"GB2-05":50.72174167918636,"GB2-06":22.41122938604782,"GB2-07":29.762789077765028},"none":{"GB2-01":41.30527687373557,"GB2-04":13.812081857942369,"GB2-05":16.202556095951337,"GB2-06":25.892494608283776,"GB2-07":13.62340547927469,"GB2-08":21.411761228695575}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.519032031014095,"none":21.208002853840444},"reasoning_agg":{"medium":{"max":50.72174167918636,"mean":26.519032031014095,"min":19.10911122360846},"none":{"max":41.30527687373557,"mean":21.208002853840444,"min":13.62340547927469}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":50.72174167918636,"reasoning_variance":5.311029177173651},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":50.72174167918636,"expected_score":28.819102756518134,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.300070725504039},"none":{"ceiling_score":41.30527687373557,"expected_score":20.52477519749719,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.6832276563432558}}},{"canonical_public_row_identity":"publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:b9a2033385dc7bc1","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":35},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.3891924000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":21},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.065385,"mean":0.03551179375,"median":0.032728425,"min":0.0200767,"recorded_attempt_count":21,"run_count":9,"total":0.3177278},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":1.2116408500000004},"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":33.06875453816814,"highest":23.68185607309067,"medium":26.79241196379518,"none":28.049988208426324},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T05:38:53Z","match_totals_all":{"draws":1761,"losses":1802,"wins":868},"match_totals_tracks":{"highest":{"draws":887,"losses":700,"wins":312},"medium":{"draws":426,"losses":474,"wins":260},"none":{"draws":448,"losses":628,"wins":296}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":54.87700656529663,"mean":23.327306091275332,"min":4.933197657130462},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":62,"overall_ranking_status":"partial","per_game":{"GB2-01":25.019855853992862,"GB2-02":8.882515737052296,"GB2-04":13.133281062064128,"GB2-05":36.2524862200164,"GB2-06":37.24502769274638,"GB2-08":21.55796987267194},"per_game_all":{"GB2-01":38.027801552864695,"GB2-06":38.79469728557749,"GB2-08":22.38376477606224},"per_game_match_totals_all":{"GB2-01":{"draws":132,"losses":260,"wins":186},"GB2-02":{"draws":530,"losses":77,"wins":7},"GB2-03":{"draws":77,"losses":52,"wins":13},"GB2-04":{"draws":323,"losses":68,"wins":31},"GB2-05":{"draws":0,"losses":298,"wins":266},"GB2-06":{"draws":33,"losses":361,"wins":263},"GB2-07":{"draws":0,"losses":415,"wins":53},"GB2-08":{"draws":666,"losses":271,"wins":49}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":56,"losses":118,"wins":38},"GB2-02":{"draws":342,"losses":46,"wins":6},"GB2-04":{"draws":159,"losses":44,"wins":13},"GB2-05":{"draws":0,"losses":225,"wins":157},"GB2-06":{"draws":17,"losses":118,"wins":76},"GB2-08":{"draws":313,"losses":149,"wins":22}},"medium":{"GB2-01":{"draws":41,"losses":73,"wins":80},"GB2-02":{"draws":188,"losses":31,"wins":1},"GB2-06":{"draws":14,"losses":90,"wins":130},"GB2-07":{"draws":0,"losses":218,"wins":32},"GB2-08":{"draws":183,"losses":62,"wins":17}},"none":{"GB2-01":{"draws":35,"losses":69,"wins":68},"GB2-03":{"draws":77,"losses":52,"wins":13},"GB2-04":{"draws":164,"losses":24,"wins":18},"GB2-05":{"draws":0,"losses":73,"wins":109},"GB2-06":{"draws":2,"losses":153,"wins":57},"GB2-07":{"draws":0,"losses":197,"wins":21},"GB2-08":{"draws":170,"losses":60,"wins":10}}},"per_game_raw_elo_all":{"GB2-01":1428.4895098506513,"GB2-06":1307.3251770467562,"GB2-08":1317.3151721186366},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1247.2566040724391,"GB2-02":1419.0805469200218,"GB2-04":1418.313093019057,"GB2-05":1297.104270967377,"GB2-06":1282.1397237244496,"GB2-08":1306.9772866587587},"medium":{"GB2-01":1486.354473050268,"GB2-02":1409.3274335688773,"GB2-06":1572.7930628110516,"GB2-07":875.3972233499316,"GB2-08":1328.1650872273349},"none":{"GB2-01":1551.8574524292462,"GB2-03":1340.1947318032933,"GB2-04":1488.972861970335,"GB2-05":1550.4189004184475,"GB2-06":1067.0427446047674,"GB2-07":863.3560394145468,"GB2-08":1316.8031424698158}},"per_game_tracks":{"highest":{"GB2-01":25.019855853992862,"GB2-02":8.882515737052296,"GB2-04":13.133281062064128,"GB2-05":36.2524862200164,"GB2-06":37.24502769274638,"GB2-08":21.55796987267194},"medium":{"GB2-01":42.22647014297127,"GB2-02":7.729979477723089,"GB2-06":54.87700656529663,"GB2-07":5.848521422546223,"GB2-08":23.280082210438678},"none":{"GB2-01":46.83707866162994,"GB2-03":21.99123517490782,"GB2-04":23.872236829208948,"GB2-05":52.140869292341534,"GB2-06":24.26205759868946,"GB2-07":4.933197657130462,"GB2-08":22.3132422450761}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":20.509088968063306,"medium":23.130961517388844,"none":26.34186778837385},"reasoning_agg":{"highest":{"max":37.24502769274638,"mean":20.509088968063306,"min":8.882515737052296},"medium":{"max":54.87700656529663,"mean":23.130961517388844,"min":5.848521422546223},"none":{"max":52.140869292341534,"mean":26.34186778837385,"min":4.933197657130462}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":54.87700656529663,"expected_score":28.04056994113851,"reasoning_variance":5.832778820310544,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.7132638498631785},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":37.24502769274638,"expected_score":12.834319854026665,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.674769114036641},"medium":{"ceiling_score":54.87700656529663,"expected_score":24.5486037335545,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.4176422161656568},"none":{"ceiling_score":52.140869292341534,"expected_score":28.6173761894864,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.2755084011125497}}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling-small:0066eef0baf981d4","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.06806129999999999,"mean":0.037113121874999995,"median":0.0310111,"min":0.0230335,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":14},"recorded_attempt_count":14,"run_count":10,"total":0.38761484999999996},"medium":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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":0.07763975000000001},"none":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"historical-provider-setting-intensive":{"admitted_cell_count":8,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.06806129999999999,"mean":0.01775885625,"median":0.0102184875,"min":0.00430875,"pricing_table_versions":{"boardgame-list-prices-2026-08-08":43},"recorded_attempt_count":43,"run_count":28,"total":0.5373186},"codegen_latency_ms":{"attempt_count":43,"max_ms":599272,"mean_ms":125847.07142857143,"min_ms":18961,"run_count":28},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":599272,"mean_ms":283663.1,"min_ms":69866,"run_count":10},"medium":{"attempt_count":15,"max_ms":68712,"mean_ms":42566.11111111111,"min_ms":22862,"run_count":9},"none":{"attempt_count":14,"max_ms":63236,"mean_ms":33776.88888888889,"min_ms":18961,"run_count":9}},"codegen_output_tokens":{"attempt_count":43,"output_max":49133,"output_mean":11683.67857142857,"output_min":894,"run_count":28},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":49133,"output_mean":28182.1,"output_min":11882,"run_count":10},"medium":{"attempt_count":15,"output_max":4066,"output_mean":2679.6666666666665,"output_min":1736,"run_count":9},"none":{"attempt_count":14,"output_max":5147,"output_mean":2356.1111111111113,"output_min":894,"run_count":9}},"display_name":"Inkling Small","economics":{"all":24.186811521612086,"highest":27.075796044285273,"medium":22.736326457591783,"none":22.74831206295921},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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":0.4444444444444444},"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":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":0.3333333333333333},"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":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":0.2}},"id":"thinkingmachines/inkling-small","is_recent_addition":false,"last_measured_at":"2026-09-26T06:22:26Z","match_totals_all":{"draws":2454,"losses":3061,"wins":1352},"match_totals_tracks":{"highest":{"draws":805,"losses":1025,"wins":575},"medium":{"draws":795,"losses":1094,"wins":443},"none":{"draws":854,"losses":942,"wins":334}},"model_slug":"thinkingmachines-inkling-small","overall":{"max":57.09812714619438,"mean":23.257180799194373,"min":3.648594419826946},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":63,"overall_ranking_status":"ranked","per_game":{"GB2-01":27.16530832402439,"GB2-02":9.977752651245442,"GB2-03":28.126696650929972,"GB2-04":14.251422456497512,"GB2-05":40.308561068609585,"GB2-06":52.37702750593773,"GB2-07":22.46093593319971,"GB2-08":21.9386637638378},"per_game_all":{"GB2-01":17.210520563827426,"GB2-02":11.300859423724527,"GB2-03":30.09863158360228,"GB2-04":16.48816689134067,"GB2-05":21.573051331885626,"GB2-06":35.0641092468338,"GB2-07":38.25048461960173,"GB2-08":23.50866851208063},"per_game_match_totals_all":{"GB2-01":{"draws":166,"losses":494,"wins":105},"GB2-02":{"draws":735,"losses":91,"wins":2},"GB2-03":{"draws":312,"losses":250,"wins":225},"GB2-04":{"draws":575,"losses":220,"wins":134},"GB2-05":{"draws":0,"losses":593,"wins":164},"GB2-06":{"draws":9,"losses":586,"wins":299},"GB2-07":{"draws":0,"losses":548,"wins":379},"GB2-08":{"draws":657,"losses":279,"wins":44}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":83,"losses":114,"wins":51},"GB2-02":{"draws":262,"losses":50,"wins":0},"GB2-03":{"draws":76,"losses":112,"wins":100},"GB2-04":{"draws":175,"losses":90,"wins":38},"GB2-05":{"draws":0,"losses":158,"wins":129},"GB2-06":{"draws":5,"losses":168,"wins":181},"GB2-07":{"draws":0,"losses":216,"wins":64},"GB2-08":{"draws":204,"losses":117,"wins":12}},"medium":{"GB2-01":{"draws":37,"losses":214,"wins":7},"GB2-02":{"draws":238,"losses":12,"wins":0},"GB2-03":{"draws":94,"losses":94,"wins":63},"GB2-04":{"draws":189,"losses":78,"wins":59},"GB2-05":{"draws":0,"losses":211,"wins":25},"GB2-06":{"draws":2,"losses":208,"wins":55},"GB2-07":{"draws":0,"losses":163,"wins":214},"GB2-08":{"draws":235,"losses":114,"wins":20}},"none":{"GB2-01":{"draws":46,"losses":166,"wins":47},"GB2-02":{"draws":235,"losses":29,"wins":2},"GB2-03":{"draws":142,"losses":44,"wins":62},"GB2-04":{"draws":211,"losses":52,"wins":37},"GB2-05":{"draws":0,"losses":224,"wins":10},"GB2-06":{"draws":2,"losses":210,"wins":63},"GB2-07":{"draws":0,"losses":169,"wins":101},"GB2-08":{"draws":218,"losses":48,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1136.8979230702687,"GB2-02":1432.0206421621651,"GB2-03":1417.9075950796916,"GB2-04":1435.736934542123,"GB2-05":1060.0460777716219,"GB2-06":1241.8233311190065,"GB2-07":1362.3840391237727,"GB2-08":1328.6564497692525},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1274.856335022027,"GB2-02":1421.0737967748826,"GB2-03":1395.7130621400465,"GB2-04":1421.3905151798865,"GB2-05":1356.2900405824616,"GB2-06":1526.523452586598,"GB2-07":1124.8863853378668,"GB2-08":1308.0953599577492},"medium":{"GB2-01":949.271767975413,"GB2-02":1441.8036532888661,"GB2-03":1364.935531559753,"GB2-04":1452.2136173772856,"GB2-05":995.7357675461593,"GB2-06":1051.2667618031494,"GB2-07":1644.67704856788,"GB2-08":1326.8458833461157},"none":{"GB2-01":1186.5656662133663,"GB2-02":1433.184476422747,"GB2-03":1493.074191539275,"GB2-04":1433.6066710691964,"GB2-05":828.1124251862449,"GB2-06":1147.6797789672723,"GB2-07":1317.588683465571,"GB2-08":1351.0281060038924}},"per_game_tracks":{"highest":{"GB2-01":27.16530832402439,"GB2-02":9.977752651245442,"GB2-03":28.126696650929972,"GB2-04":14.251422456497512,"GB2-05":40.308561068609585,"GB2-06":52.37702750593773,"GB2-07":22.46093593319971,"GB2-08":21.9386637638378},"medium":{"GB2-01":3.648594419826946,"GB2-02":12.512379848663569,"GB2-03":25.084613622618456,"GB2-04":19.105334507144274,"GB2-05":17.480037443390213,"GB2-06":23.48355859743308,"GB2-07":57.09812714619438,"GB2-08":23.477966075463343},"none":{"GB2-01":20.817658947630942,"GB2-02":11.41244577126457,"GB2-03":37.0845844772584,"GB2-04":16.10774371038022,"GB2-05":6.930555483657085,"GB2-06":29.331741637130598,"GB2-07":35.1923907794111,"GB2-08":25.10937569694075}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":25.60670691596418,"medium":22.076598828024654,"none":22.08823665359429},"reasoning_agg":{"highest":{"max":52.37702750593773,"mean":25.60670691596418,"min":9.977752651245442},"medium":{"max":57.09812714619438,"mean":22.076598828024654,"min":3.648594419826946},"none":{"max":37.0845844772584,"mean":22.08823665359429,"min":6.930555483657085}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":57.09812714619438,"expected_score":19.629427630623788,"reasoning_variance":3.5301080879395244,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.6277531685705853},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":52.37702750593773,"expected_score":16.407314089011425,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.199392826952753},"medium":{"ceiling_score":57.09812714619438,"expected_score":19.485448038034125,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.591150789990529},"none":{"ceiling_score":37.0845844772584,"expected_score":22.99552076482582,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.9072841112315295}}},{"canonical_public_row_identity":"publication-row.v1:overall:minimax-minimax-m3:6106413b060d69af","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.09803328,"mean":0.049222395,"median":0.05336871,"min":0.00639384,"recorded_attempt_count":30,"run_count":16,"total":0.78755832},"codegen_latency_ms":{"attempt_count":30,"max_ms":689304,"mean_ms":337511.375,"min_ms":47263,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":689304,"mean_ms":510017.125,"min_ms":355427,"run_count":8},"none":{"attempt_count":13,"max_ms":622847,"mean_ms":165005.625,"min_ms":47263,"run_count":8}},"codegen_output_tokens":{"attempt_count":30,"output_max":78058,"output_mean":37255.0,"output_min":3462,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":76773,"output_mean":56941.375,"output_min":40677,"run_count":8},"none":{"attempt_count":13,"output_max":78058,"output_mean":17568.625,"output_min":3462,"run_count":8}},"display_name":"Minimax M3","economics":{"medium":18.383514849331107,"none":30.43906736199609},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T06:57:54Z","match_totals_all":{"draws":891,"losses":1417,"wins":756},"match_totals_tracks":{"medium":{"draws":578,"losses":805,"wins":301},"none":{"draws":313,"losses":612,"wins":455}},"model_slug":"minimax-minimax-m3","overall":{"max":41.677573480494466,"mean":23.053347573203013,"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":64,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":54,"losses":216,"wins":154},"GB2-02":{"draws":381,"losses":76,"wins":1},"GB2-03":{"draws":59,"losses":65,"wins":56},"GB2-04":{"draws":174,"losses":36,"wins":20},"GB2-05":{"draws":0,"losses":388,"wins":96},"GB2-06":{"draws":2,"losses":167,"wins":77},"GB2-07":{"draws":0,"losses":292,"wins":216},"GB2-08":{"draws":221,"losses":177,"wins":136}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":11,"losses":136,"wins":51},"GB2-02":{"draws":187,"losses":31,"wins":0},"GB2-04":{"draws":174,"losses":36,"wins":20},"GB2-05":{"draws":0,"losses":248,"wins":4},"GB2-06":{"draws":2,"losses":167,"wins":77},"GB2-07":{"draws":0,"losses":125,"wins":133},"GB2-08":{"draws":204,"losses":62,"wins":16}},"none":{"GB2-01":{"draws":43,"losses":80,"wins":103},"GB2-02":{"draws":194,"losses":45,"wins":1},"GB2-03":{"draws":59,"losses":65,"wins":56},"GB2-05":{"draws":0,"losses":140,"wins":92},"GB2-07":{"draws":0,"losses":167,"wins":83},"GB2-08":{"draws":17,"losses":115,"wins":120}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1159.3263773780907,"GB2-02":1423.5265844926153,"GB2-04":1389.1005875466244,"GB2-05":716.9732845937543,"GB2-06":1109.0858039881675,"GB2-07":1416.082190836369,"GB2-08":1323.8629310433298},"none":{"GB2-01":1463.017538611488,"GB2-02":1396.292716777849,"GB2-03":1455.5668229698092,"GB2-05":1254.7163305285064,"GB2-07":1219.1763853657092,"GB2-08":1548.7742440728048}},"per_game_tracks":{"medium":{"GB2-01":18.59051543287467,"GB2-02":9.702121884307711,"GB2-04":8.780614205603722,"GB2-05":0.0,"GB2-06":26.91858974316353,"GB2-07":41.677573480494466,"GB2-08":23.01518919887364},"none":{"GB2-01":40.6898977490923,"GB2-02":6.063607336465111,"GB2-03":33.15700207288683,"GB2-05":33.754455721721605,"GB2-07":28.612859582480787,"GB2-08":40.3565817093299}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#f2fffc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":17.77995115279634,"none":28.326743993609693},"reasoning_agg":{"medium":{"max":41.677573480494466,"mean":17.77995115279634,"min":0.0},"none":{"max":40.6898977490923,"mean":28.326743993609693,"min":6.063607336465111}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":41.677573480494466,"reasoning_variance":10.546792840813353},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":41.677573480494466,"expected_score":15.69141746935887,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.08853368343747},"none":{"ceiling_score":40.6898977490923,"expected_score":32.922548802184856,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.5958048085751635}}},{"canonical_public_row_identity":"publication-row.v1:overall:thinkingmachines-inkling:f3e37953cb77674a","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":9,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"none":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":4,"max":0.0721503,"mean":0.03677837187500001,"median":0.0324098875,"min":0.01945095,"recorded_attempt_count":39,"run_count":16,"total":0.58845395}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":10,"max":0.11839474,"mean":0.07845433000000002,"median":0.08046371000000001,"min":0.036046930000000005,"recorded_attempt_count":53,"run_count":16,"total":1.2552692799999998},"historical-provider-setting-baseline":{"admitted_cell_count":12,"cell_count":8,"cost_basis_counts":{"provider_reported":39},"cost_is_complete":false,"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},"cost_is_complete":false,"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":4.1572507100000005}},"codegen_cost_usd":{"admitted_cell_count":27,"cell_count":24,"cost_basis_counts":{"provider_reported":145},"cost_is_complete":false,"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":26.77203425680087,"highest":26.97781240959458,"medium":23.61402092490127,"none":28.51186178565159},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T03:02:58Z","match_totals_all":{"draws":2666,"losses":3979,"wins":1841},"match_totals_tracks":{"highest":{"draws":1173,"losses":1758,"wins":761},"medium":{"draws":714,"losses":1054,"wins":414},"none":{"draws":779,"losses":1167,"wins":666}},"model_slug":"thinkingmachines-inkling","overall":{"max":61.785043322570075,"mean":22.791906005520094,"min":8.546310409277053},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":65,"overall_ranking_status":"partial","per_game":{"GB2-01":27.52065330833926,"GB2-02":8.783968184895329,"GB2-03":30.79894699051619,"GB2-04":19.71364335262243,"GB2-05":21.619082747737878,"GB2-06":53.93750226906707,"GB2-07":35.60200739499908,"GB2-08":17.84669502857943},"per_game_all":{"GB2-01":27.174625334139296,"GB2-03":36.98090128244633,"GB2-04":12.446487507003718,"GB2-05":25.12700766931856,"GB2-07":24.9965901121372,"GB2-08":33.9065936357601},"per_game_match_totals_all":{"GB2-01":{"draws":406,"losses":634,"wins":120},"GB2-02":{"draws":539,"losses":63,"wins":8},"GB2-03":{"draws":327,"losses":364,"wins":388},"GB2-04":{"draws":838,"losses":262,"wins":132},"GB2-05":{"draws":0,"losses":1050,"wins":364},"GB2-06":{"draws":20,"losses":408,"wins":342},"GB2-07":{"draws":0,"losses":790,"wins":272},"GB2-08":{"draws":536,"losses":408,"wins":215}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":139,"losses":208,"wins":17},"GB2-02":{"draws":337,"losses":41,"wins":4},"GB2-03":{"draws":159,"losses":152,"wins":123},"GB2-04":{"draws":266,"losses":93,"wins":67},"GB2-05":{"draws":0,"losses":613,"wins":155},"GB2-06":{"draws":15,"losses":228,"wins":257},"GB2-07":{"draws":0,"losses":270,"wins":134},"GB2-08":{"draws":257,"losses":153,"wins":4}},"medium":{"GB2-01":{"draws":118,"losses":184,"wins":68},"GB2-03":{"draws":62,"losses":111,"wins":168},"GB2-04":{"draws":266,"losses":60,"wins":14},"GB2-05":{"draws":0,"losses":171,"wins":71},"GB2-07":{"draws":0,"losses":349,"wins":57},"GB2-08":{"draws":268,"losses":179,"wins":36}},"none":{"GB2-01":{"draws":149,"losses":242,"wins":35},"GB2-02":{"draws":202,"losses":22,"wins":4},"GB2-03":{"draws":106,"losses":101,"wins":97},"GB2-04":{"draws":306,"losses":109,"wins":51},"GB2-05":{"draws":0,"losses":266,"wins":138},"GB2-06":{"draws":5,"losses":180,"wins":85},"GB2-07":{"draws":0,"losses":171,"wins":81},"GB2-08":{"draws":11,"losses":76,"wins":175}}},"per_game_raw_elo_all":{"GB2-01":1272.6609960438147,"GB2-03":1491.0021111768956,"GB2-04":1409.0710268522027,"GB2-05":1116.0500922798717,"GB2-07":1160.9340277677786,"GB2-08":1461.3095713228051},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1275.3565404729725,"GB2-02":1410.3826257930446,"GB2-03":1419.8634319347743,"GB2-04":1453.4167361220593,"GB2-05":1055.9492963703817,"GB2-06":1549.0099393053554,"GB2-07":1319.352462162114,"GB2-08":1253.0956042771386},"medium":{"GB2-01":1313.928445550254,"GB2-03":1570.3276594569068,"GB2-04":1382.916212533841,"GB2-05":1086.0713160839841,"GB2-07":975.9842035803725,"GB2-08":1306.315735107093},"none":{"GB2-01":1228.6980021082184,"GB2-02":1426.8249346820382,"GB2-03":1482.815242139006,"GB2-04":1390.880131900708,"GB2-05":1206.1296643852497,"GB2-06":1171.1525322119405,"GB2-07":1187.465417560849,"GB2-08":1824.517374584184}},"per_game_tracks":{"highest":{"GB2-01":27.52065330833926,"GB2-02":8.783968184895329,"GB2-03":30.79894699051619,"GB2-04":19.71364335262243,"GB2-05":21.619082747737878,"GB2-06":53.93750226906707,"GB2-07":35.60200739499908,"GB2-08":17.84669502857943},"medium":{"GB2-01":30.323203416606013,"GB2-03":44.676528820951454,"GB2-04":8.546310409277053,"GB2-05":23.181924158654972,"GB2-07":12.868116187787319,"GB2-08":22.0880425561308},"none":{"GB2-01":23.680019277472617,"GB2-02":10.247829809189867,"GB2-03":35.467228035871344,"GB2-04":9.079508759111675,"GB2-05":30.580016101562823,"GB2-06":30.735602225809092,"GB2-07":26.519646753625203,"GB2-08":61.785043322570075}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.363470885239984,"medium":18.47897001154546,"none":26.533277119774834},"reasoning_agg":{"highest":{"max":53.93750226906707,"mean":23.363470885239984,"min":8.783968184895329},"medium":{"max":44.676528820951454,"mean":18.47897001154546,"min":8.546310409277053},"none":{"max":61.785043322570075,"mean":26.533277119774834,"min":9.079508759111675}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":61.785043322570075,"expected_score":23.67092174391222,"reasoning_variance":8.054307108229374,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.8790157383921269},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.93750226906707,"expected_score":15.80824320063465,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.555227684605335},"medium":{"ceiling_score":44.676528820951454,"expected_score":23.99742476459856,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.518454753053099},"none":{"ceiling_score":61.785043322570075,"expected_score":29.96411082594674,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.4308337061719065}}},{"canonical_public_row_identity":"publication-row.v1:overall:xiaomi-mimo-v2-5:7ea22dc2e757d29f","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.48618750699999996},"none":{"admitted_cell_count":17,"cell_count":8,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.2720731754},"historical-provider-setting-balanced-variant-2":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":20},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.038769960000000006,"mean":0.023744302225,"median":0.0230069837,"min":0.0074361952000000005,"recorded_attempt_count":20,"run_count":9,"total":0.2141143316},"historical-provider-setting-baseline-variant-1":{"admitted_cell_count":11,"cell_count":8,"cost_basis_counts":{"provider_reported":25},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.030685472800000002},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0597184625,"mean":0.02467013555,"median":0.0239011175,"min":0.0040410944,"recorded_attempt_count":19,"run_count":8,"total":0.1973610844}},"codegen_cost_usd":{"admitted_cell_count":37,"cell_count":24,"cost_basis_counts":{"provider_reported":108},"cost_is_complete":false,"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":0.7524538071999999},"codegen_latency_ms":{"attempt_count":32,"max_ms":2480898,"mean_ms":755138.0,"min_ms":19112,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":20,"max_ms":2480898,"mean_ms":1257942.2222222222,"min_ms":113183,"run_count":9},"none":{"attempt_count":12,"max_ms":1141174,"mean_ms":189483.25,"min_ms":19112,"run_count":8}},"codegen_output_tokens":{"attempt_count":32,"output_max":131072,"output_mean":43207.23529411765,"output_min":1607,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":20,"output_max":131072,"output_mean":76516.0,"output_min":16030,"run_count":9},"none":{"attempt_count":12,"output_max":24962,"output_mean":5734.875,"output_min":1607,"run_count":8}},"display_name":"MiMo-V2.5","economics":{"all":22.50086946372286,"highest":24.802908586552224,"medium":23.96969229855238,"none":25.336392906680977},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T05:37:05Z","match_totals_all":{"draws":2937,"losses":3357,"wins":1720},"match_totals_tracks":{"highest":{"draws":612,"losses":321,"wins":121},"medium":{"draws":1340,"losses":1376,"wins":710},"none":{"draws":985,"losses":1660,"wins":889}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":49.18568960987756,"mean":22.26104303261306,"min":6.897762277920762},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings"],"overall_official_rank":66,"overall_ranking_status":"partial","per_game":{"GB2-01":22.243381892513856,"GB2-02":13.400166752240317,"GB2-04":15.209229931824503,"GB2-06":49.18568960987756,"GB2-08":23.97607474630488},"per_game_all":{"GB2-01":28.011497427443114,"GB2-02":10.55138345117002,"GB2-04":14.833138151186683,"GB2-06":37.483943106318314,"GB2-08":21.624385182496166},"per_game_match_totals_all":{"GB2-01":{"draws":248,"losses":569,"wins":331},"GB2-02":{"draws":913,"losses":139,"wins":32},"GB2-03":{"draws":74,"losses":43,"wins":37},"GB2-04":{"draws":923,"losses":270,"wins":107},"GB2-05":{"draws":0,"losses":633,"wins":387},"GB2-06":{"draws":32,"losses":657,"wins":429},"GB2-07":{"draws":0,"losses":633,"wins":333},"GB2-08":{"draws":747,"losses":413,"wins":64}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":86,"losses":76,"wins":2},"GB2-02":{"draws":161,"losses":34,"wins":9},"GB2-04":{"draws":164,"losses":40,"wins":16},"GB2-06":{"draws":15,"losses":122,"wins":91},"GB2-08":{"draws":186,"losses":49,"wins":3}},"medium":{"GB2-01":{"draws":50,"losses":216,"wins":134},"GB2-02":{"draws":572,"losses":78,"wins":22},"GB2-04":{"draws":452,"losses":151,"wins":51},"GB2-05":{"draws":0,"losses":271,"wins":187},"GB2-06":{"draws":11,"losses":170,"wins":69},"GB2-07":{"draws":0,"losses":297,"wins":189},"GB2-08":{"draws":255,"losses":193,"wins":58}},"none":{"GB2-01":{"draws":112,"losses":277,"wins":195},"GB2-02":{"draws":180,"losses":27,"wins":1},"GB2-03":{"draws":74,"losses":43,"wins":37},"GB2-04":{"draws":307,"losses":79,"wins":40},"GB2-05":{"draws":0,"losses":362,"wins":200},"GB2-06":{"draws":6,"losses":365,"wins":269},"GB2-07":{"draws":0,"losses":336,"wins":144},"GB2-08":{"draws":306,"losses":171,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1295.0755434308337,"GB2-02":1435.3517308021874,"GB2-04":1434.5857728649692,"GB2-06":1289.7522906354461,"GB2-08":1312.7513097104845},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1226.593007890141,"GB2-02":1466.9626250177785,"GB2-04":1447.1377370777318,"GB2-06":1493.4286294877206,"GB2-08":1353.3754613515255},"medium":{"GB2-01":1296.6878985098956,"GB2-02":1434.9435865561327,"GB2-04":1415.3607108396243,"GB2-05":1254.80778562274,"GB2-06":1132.0001824283734,"GB2-07":1232.2060406998135,"GB2-08":1334.2450698022235},"none":{"GB2-01":1361.9457238924642,"GB2-02":1404.1489808326505,"GB2-03":1468.760328846214,"GB2-04":1441.258870677551,"GB2-05":1280.8391330619731,"GB2-06":1243.8280599902446,"GB2-07":1156.390706939917,"GB2-08":1250.633397977705}},"per_game_tracks":{"highest":{"GB2-01":22.243381892513856,"GB2-02":13.400166752240317,"GB2-04":15.209229931824503,"GB2-06":49.18568960987756,"GB2-08":23.97607474630488},"medium":{"GB2-01":28.53544326324446,"GB2-02":11.356221323348983,"GB2-04":12.668068900787802,"GB2-05":33.748540263721935,"GB2-06":28.314380280149376,"GB2-07":29.44797139696061,"GB2-08":23.717220661653492},"none":{"GB2-01":33.255667126571026,"GB2-02":6.897762277920762,"GB2-03":34.16927162164882,"GB2-04":16.62211562094775,"GB2-05":35.19376127960801,"GB2-06":34.951759428928,"GB2-07":24.42094575829332,"GB2-08":17.179860139530124}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":22.05325082427171,"medium":21.659061986883398,"none":23.070816286684074},"reasoning_agg":{"highest":{"max":49.18568960987756,"mean":22.05325082427171,"min":13.400166752240317},"medium":{"max":33.748540263721935,"mean":21.659061986883398,"min":11.356221323348983},"none":{"max":35.19376127960801,"mean":23.070816286684074,"min":6.897762277920762}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":49.18568960987756,"expected_score":18.580760795796017,"reasoning_variance":1.411754299800677,"reliability_score":96.10465568271802,"uncertainty_avg":3.895344317281976,"uncertainty_penalty":-3.6802822368170425},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":49.18568960987756,"expected_score":16.46955189092964,"reliability_score":88.31396704815407,"uncertainty_avg":11.686032951845927,"uncertainty_penalty":-5.58369893334207},"medium":{"ceiling_score":33.748540263721935,"expected_score":22.15156782080092,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.492505833917523},"none":{"ceiling_score":35.19376127960801,"expected_score":26.206009922558113,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.135193635874039}}},{"canonical_public_row_identity":"publication-row.v1:overall:mistralai-mistral-medium-3-5:d99706c7568df32b","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.27741402547937455,"mean":0.17469283299791016,"median":0.15577176465417142,"min":0.1042008119864669,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":13},"run_count":8,"token_priced_attempt_count":13,"total":1.397542663983281},"none":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":12},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.11538050836051075,"mean":0.06762316700208985,"median":0.06087263456058671,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"run_count":8,"token_priced_attempt_count":12,"total":0.5409853360167188}},"codegen_cost_by_setting":{"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":12},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.11538050836051075,"mean":0.06762316700208985,"median":0.06087263456058671,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":12},"run_count":8,"token_priced_attempt_count":12,"total":0.5409853360167188},"historical-provider-setting-intensive":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"local_list_price_estimate":13},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":1,"max":0.27741402547937455,"mean":0.17469283299791016,"median":0.15577176465417142,"min":0.1042008119864669,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":13},"run_count":8,"token_priced_attempt_count":13,"total":1.397542663983281}},"codegen_cost_usd":{"admitted_cell_count":14,"cell_count":16,"cost_basis_counts":{"local_list_price_estimate":25},"cost_is_complete":true,"evidence_basis":"Standard list-price estimate","failed_cell_count":2,"max":0.27741402547937455,"mean":0.12115799999999999,"median":0.10979066017348882,"min":0.04290565490575157,"pricing_table_versions":{"boardgame-list-prices-2026-09-08":25},"run_count":16,"token_priced_attempt_count":25,"total":1.9385279999999998},"codegen_output_tokens":{"attempt_count":25,"output_max":39199,"output_mean":13770.375,"output_min":1490,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":13,"output_max":39199,"output_mean":24874.75,"output_min":14259,"run_count":8},"none":{"attempt_count":12,"output_max":5186,"output_mean":2666.0,"output_min":1490,"run_count":8}},"display_name":"Mistral Medium 3.5","economics":{"highest":25.64687563293779,"none":18.362746573701774},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"effective_max_output_token_observations":25,"effective_max_output_tokens":[209715],"finish_reason_observations":25,"finish_reasons":["stop"],"indexed_attempts":25,"output_token_observations":25,"provider_post_attempt_observations":25,"provider_post_attempts":34,"reasoning_token_observations":25,"reconciliation_get_attempt_observations":25,"requested_max_output_token_observations":25,"requested_max_output_tokens":[209715],"total_output_tokens":220326,"total_visible_output_tokens":220326,"visible_token_observations":25},"generation_policy":{"generation_policy":"quality_generation_policy","stream_idle_timeout_seconds":null,"streaming_enabled":null,"strict_wall_clock_timeout_seconds":null,"timeout_mode":"provider_route_timeout_guard"},"generation_timing":{"finish_reason":"stop","first_progress_after_seconds":null,"generation_completed_at":null,"generation_started_at":null,"generation_wall_clock_seconds":null,"stream_progress_event_count":null},"reasoning_provenance":{"code_output_mode":"unknown_legacy","code_prompt_version":"unknown_legacy","generation_settings_public":{"max_tokens":209715,"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":["GB2-07"],"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":7,"evaluated_cells":8,"failed_game_aliases":["GB2-01"],"first_pass_admitted":3,"first_pass_rate":0.375,"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":4,"repaired_rate":0.5}},"id":"mistralai/mistral-medium-3-5","is_recent_addition":false,"last_measured_at":"2026-09-26T04:46:57Z","match_totals_all":{"draws":1358,"losses":1716,"wins":575},"match_totals_tracks":{"highest":{"draws":729,"losses":835,"wins":370},"none":{"draws":629,"losses":881,"wins":205}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":54.25243035998023,"mean":21.28235376913093,"min":3.8697286850747075},"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":67,"overall_ranking_status":"partial","per_game":{"GB2-02":12.199265534511687,"GB2-03":31.17046637446215,"GB2-04":14.273135505042317,"GB2-05":54.25243035998023,"GB2-06":30.74300154707384,"GB2-07":15.963538315872162,"GB2-08":20.926291793622116},"per_game_match_totals_all":{"GB2-01":{"draws":27,"losses":200,"wins":11},"GB2-02":{"draws":456,"losses":97,"wins":11},"GB2-03":{"draws":156,"losses":193,"wins":129},"GB2-04":{"draws":308,"losses":139,"wins":46},"GB2-05":{"draws":0,"losses":309,"wins":185},"GB2-06":{"draws":15,"losses":355,"wins":120},"GB2-07":{"draws":0,"losses":252,"wins":42},"GB2-08":{"draws":396,"losses":171,"wins":31}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":248,"losses":49,"wins":11},"GB2-03":{"draws":81,"losses":91,"wins":60},"GB2-04":{"draws":187,"losses":49,"wins":20},"GB2-05":{"draws":0,"losses":114,"wins":150},"GB2-06":{"draws":13,"losses":162,"wins":71},"GB2-07":{"draws":0,"losses":252,"wins":42},"GB2-08":{"draws":200,"losses":118,"wins":16}},"none":{"GB2-01":{"draws":27,"losses":200,"wins":11},"GB2-02":{"draws":208,"losses":48,"wins":0},"GB2-03":{"draws":75,"losses":102,"wins":69},"GB2-04":{"draws":121,"losses":90,"wins":26},"GB2-05":{"draws":0,"losses":195,"wins":35},"GB2-06":{"draws":2,"losses":193,"wins":49},"GB2-08":{"draws":196,"losses":53,"wins":15}}},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1437.0761650218744,"GB2-03":1430.8522616854088,"GB2-04":1423.5418124414398,"GB2-05":1578.9950567462552,"GB2-06":1172.4282055443878,"GB2-07":1026.1918345359104,"GB2-08":1295.0125800246592},"none":{"GB2-01":953.347742642718,"GB2-02":1397.7095733713916,"GB2-03":1438.693137987166,"GB2-04":1411.7001560849312,"GB2-05":1113.9078239025785,"GB2-06":1076.5200179669243,"GB2-08":1339.5770773929355}},"per_game_tracks":{"highest":{"GB2-02":12.199265534511687,"GB2-03":31.17046637446215,"GB2-04":14.273135505042317,"GB2-05":54.25243035998023,"GB2-06":30.74300154707384,"GB2-07":15.963538315872162,"GB2-08":20.926291793622116},"none":{"GB2-01":3.8697286850747075,"GB2-02":6.376285948130186,"GB2-03":31.976265207526513,"GB2-04":12.306930278603543,"GB2-05":24.89129225069476,"GB2-06":24.946112253775144,"GB2-08":24.17261139210758}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#fff8f3","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":24.8048428014335,"none":17.75986473682835},"reasoning_agg":{"highest":{"max":54.25243035998023,"mean":24.8048428014335,"min":12.199265534511687},"none":{"max":31.976265207526513,"mean":17.75986473682835,"min":3.8697286850747075}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":54.25243035998023,"reasoning_variance":7.04497806460515},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.25243035998023,"expected_score":14.115980638292147,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.688862163141355},"none":{"ceiling_score":31.976265207526513,"expected_score":17.431433196400523,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.32843154042782885}}},{"canonical_public_row_identity":"publication-row.v1:overall:cohere-north-mini-code:bb91725eb139a0ce","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":15},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":27.7309150125342,"none":20.543714625073992},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":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":0.375},"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":768,"losses":1368,"wins":502},"match_totals_tracks":{"medium":{"draws":408,"losses":681,"wins":333},"none":{"draws":360,"losses":687,"wins":169}},"model_slug":"cohere-north-mini-code","overall":{"max":49.70554587119343,"mean":20.583266785596084,"min":13.694393813908178},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality","below_generation_quality_threshold","fixed_coverage_incomplete"],"overall_official_rank":68,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":154,"losses":258,"wins":44},"GB2-03":{"draws":46,"losses":97,"wins":13},"GB2-04":{"draws":175,"losses":50,"wins":15},"GB2-05":{"draws":0,"losses":108,"wins":132},"GB2-06":{"draws":3,"losses":173,"wins":60},"GB2-07":{"draws":0,"losses":541,"wins":229},"GB2-08":{"draws":390,"losses":141,"wins":9}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":46,"losses":97,"wins":13},"GB2-04":{"draws":175,"losses":50,"wins":15},"GB2-05":{"draws":0,"losses":108,"wins":132},"GB2-06":{"draws":3,"losses":173,"wins":60},"GB2-07":{"draws":0,"losses":185,"wins":113},"GB2-08":{"draws":184,"losses":68,"wins":0}},"none":{"GB2-01":{"draws":154,"losses":258,"wins":44},"GB2-07":{"draws":0,"losses":356,"wins":116},"GB2-08":{"draws":206,"losses":73,"wins":9}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1300.2960299618924,"GB2-04":1437.785189310206,"GB2-05":1521.6815882894657,"GB2-06":1202.388775066718,"GB2-07":1324.0836292597942,"GB2-08":1315.9793752596775},"none":{"GB2-01":1161.4164335429166,"GB2-07":1110.6567826067458,"GB2-08":1302.5551864292363}},"per_game_tracks":{"medium":{"GB2-03":15.692524768806955,"GB2-04":13.694393813908178,"GB2-05":49.70554587119343,"GB2-06":31.567720932537174,"GB2-07":34.70265553964255,"GB2-08":21.02264914911694},"none":{"GB2-01":18.878092736445947,"GB2-07":21.371580653505006,"GB2-08":21.381470485271024}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":25.806524258011688,"none":15.360009313180479},"reasoning_agg":{"medium":{"max":49.70554587119343,"mean":25.806524258011688,"min":13.694393813908178},"none":{"max":21.381470485271024,"mean":15.360009313180479,"min":18.878092736445947}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":49.70554587119343,"reasoning_variance":10.44651494483121},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":49.70554587119343,"expected_score":27.53842418933395,"reliability_score":85.14861785164499,"uncertainty_avg":14.851382148355015,"uncertainty_penalty":1.7318999313222605},"none":{"ceiling_score":21.381470485271024,"expected_score":20.27667458159659,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.9166652684161125}}},{"canonical_public_row_identity":"publication-row.v1:overall:inception-mercury-2-5-preview:0488ec4b2b7f9fb1","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0021869100000000002,"mean":0.0013222775000000001,"median":0.001054655,"min":0.00083106,"recorded_attempt_count":11,"run_count":8,"total":0.010578220000000001},"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.010122240000000001},"none":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.007612510000000001}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":12},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0025894200000000003,"mean":0.0012652800000000001,"median":0.000871045,"min":0.00078866,"recorded_attempt_count":12,"run_count":8,"total":0.01012224},"historical-provider-setting-baseline":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":14},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":3,"max":0.0013895600000000002,"mean":0.0009515637499999999,"median":0.001025285,"min":0.00044038,"recorded_attempt_count":14,"run_count":8,"total":0.00761251},"historical-provider-setting-intensive":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":11},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":2,"max":0.0021869100000000002,"mean":0.0013222775000000001,"median":0.001054655,"min":0.00083106,"recorded_attempt_count":11,"run_count":8,"total":0.010578220000000001}},"codegen_cost_usd":{"admitted_cell_count":17,"cell_count":24,"cost_basis_counts":{"provider_reported":37},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.0025894200000000003,"mean":0.0011797070833333334,"median":0.000945325,"min":0.00044038,"recorded_attempt_count":37,"run_count":24,"total":0.02831297},"codegen_latency_ms":{"attempt_count":37,"max_ms":49328,"mean_ms":21505.916666666668,"min_ms":9355,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":47445,"mean_ms":22491.5,"min_ms":13295,"run_count":8},"medium":{"attempt_count":12,"max_ms":49328,"mean_ms":23044.25,"min_ms":13295,"run_count":8},"none":{"attempt_count":14,"max_ms":24913,"mean_ms":18982.0,"min_ms":9355,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":11394,"output_mean":4854.291666666667,"output_min":1030,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":11185,"output_mean":6150.25,"output_min":2902,"run_count":8},"medium":{"attempt_count":12,"output_max":11394,"output_mean":5469.5,"output_min":3022,"run_count":8},"none":{"attempt_count":14,"output_max":4416,"output_mean":2943.125,"output_min":1030,"run_count":8}},"display_name":"Mercury 2.5 Preview","economics":{"all":19.151617745729283,"highest":19.616598160327396,"medium":18.36132215878707,"none":26.600344147420845},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":37,"finish_reasons":["stop"],"indexed_attempts":37,"output_token_observations":37,"provider_post_attempt_observations":37,"provider_post_attempts":37,"reasoning_token_observations":37,"reconciliation_get_attempt_observations":37,"reconciliation_get_attempts":176,"total_output_tokens":116503,"total_reasoning_output_tokens":61584,"total_visible_output_tokens":54919,"visible_token_observations":37},"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":"inception/mercury-2.5-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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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","GB2-03"],"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":5,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-07","GB2-08"],"first_pass_admitted":2,"first_pass_rate":0.25,"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":3,"repaired_rate":0.375},"intensive":{"admitted_plugins":6,"evaluated_cells":8,"failed_game_aliases":["GB2-03","GB2-05"],"first_pass_admitted":5,"first_pass_rate":0.625,"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":1,"repaired_rate":0.125}},"id":"inception/mercury-2.5-preview","is_recent_addition":false,"last_measured_at":"2026-09-26T06:47:23Z","match_totals_all":{"draws":1895,"losses":2047,"wins":628},"match_totals_tracks":{"highest":{"draws":726,"losses":760,"wins":162},"medium":{"draws":612,"losses":763,"wins":166},"none":{"draws":557,"losses":524,"wins":300}},"model_slug":"inception-mercury-2-5-preview","overall":{"max":39.8633838185863,"mean":19.664619778738068,"min":9.759412628410004},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":69,"overall_ranking_status":"ranked","per_game":{"GB2-01":31.38978191750631,"GB2-02":14.268634938860215,"GB2-04":15.44815996175953,"GB2-06":23.336125539304433,"GB2-07":15.222218162246332,"GB2-08":18.034668442287547},"per_game_all":{"GB2-02":12.886938898183795,"GB2-04":18.966657102386247,"GB2-06":25.60125723661781},"per_game_match_totals_all":{"GB2-01":{"draws":81,"losses":147,"wins":52},"GB2-02":{"draws":711,"losses":80,"wins":1},"GB2-03":{"draws":103,"losses":139,"wins":89},"GB2-04":{"draws":596,"losses":127,"wins":50},"GB2-05":{"draws":0,"losses":350,"wins":178},"GB2-06":{"draws":6,"losses":566,"wins":164},"GB2-07":{"draws":0,"losses":497,"wins":75},"GB2-08":{"draws":398,"losses":141,"wins":19}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":81,"losses":147,"wins":52},"GB2-02":{"draws":249,"losses":24,"wins":1},"GB2-04":{"draws":207,"losses":50,"wins":15},"GB2-06":{"draws":3,"losses":198,"wins":45},"GB2-07":{"draws":0,"losses":254,"wins":42},"GB2-08":{"draws":186,"losses":87,"wins":7}},"medium":{"GB2-02":{"draws":221,"losses":13,"wins":0},"GB2-04":{"draws":177,"losses":44,"wins":16},"GB2-05":{"draws":0,"losses":217,"wins":51},"GB2-06":{"draws":2,"losses":192,"wins":54},"GB2-07":{"draws":0,"losses":243,"wins":33},"GB2-08":{"draws":212,"losses":54,"wins":12}},"none":{"GB2-02":{"draws":241,"losses":43,"wins":0},"GB2-03":{"draws":103,"losses":139,"wins":89},"GB2-04":{"draws":212,"losses":33,"wins":19},"GB2-05":{"draws":0,"losses":133,"wins":127},"GB2-06":{"draws":1,"losses":176,"wins":65}}},"per_game_raw_elo_all":{"GB2-02":1443.8653637632915,"GB2-04":1454.0924907872802,"GB2-06":1087.3026845179966},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1331.7676493391398,"GB2-02":1453.2124126480264,"GB2-04":1430.4600611893773,"GB2-06":1049.7506963175947,"GB2-07":1014.9181276937093,"GB2-08":1259.7454672181777},"medium":{"GB2-02":1422.9991366173588,"GB2-04":1452.6206435261033,"GB2-05":1065.954692652266,"GB2-06":1080.2611802944828,"GB2-07":951.4254052763505,"GB2-08":1332.6078892288942},"none":{"GB2-02":1455.384542024489,"GB2-03":1385.897284418221,"GB2-04":1479.1967676463596,"GB2-05":1350.401005084952,"GB2-06":1131.896176941912}},"per_game_tracks":{"highest":{"GB2-01":31.38978191750631,"GB2-02":14.268634938860215,"GB2-04":15.44815996175953,"GB2-06":23.336125539304433,"GB2-07":15.222218162246332,"GB2-08":18.034668442287547},"medium":{"GB2-02":9.759412628410004,"GB2-04":18.583650159387755,"GB2-05":21.99667956346245,"GB2-06":25.184434892116496,"GB2-07":10.963344376355602,"GB2-08":23.68041133299009},"none":{"GB2-02":14.632769127281168,"GB2-03":27.35419532679281,"GB2-04":22.868161186011452,"GB2-05":39.8633838185863,"GB2-06":28.283211278432493}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":18.25530156705398,"medium":17.0871356205063,"none":23.651422148653925},"reasoning_agg":{"highest":{"max":31.38978191750631,"mean":18.25530156705398,"min":14.268634938860215},"medium":{"max":25.184434892116496,"mean":17.0871356205063,"min":9.759412628410004},"none":{"max":39.8633838185863,"mean":23.651422148653925,"min":14.632769127281168}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":39.8633838185863,"expected_score":13.159558877232792,"reasoning_variance":6.564286528147626,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.505060901505276},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":31.38978191750631,"expected_score":8.567181076666824,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.688120490387156},"medium":{"ceiling_score":25.184434892116496,"expected_score":15.823270803577245,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.263864816929054},"none":{"ceiling_score":39.8633838185863,"expected_score":27.79627999021637,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.144857841562445}}},{"canonical_public_row_identity":"publication-row.v1:overall:nex-agi-nex-n2-pro:80ab6d29e00cc243","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"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},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":false,"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},"historical-provider-setting-baseline":{"admitted_cell_count":7,"cell_count":8,"cost_basis_counts":{"provider_reported":36},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":9,"max":0.215758025,"mean":0.16162675,"median":0.1594081875,"min":0.098579625,"recorded_attempt_count":36,"run_count":16,"total":2.5860279999999998}},"codegen_cost_usd":{"admitted_cell_count":12,"cell_count":16,"cost_basis_counts":{"provider_reported":53},"cost_is_complete":false,"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":3.4057992500000003},"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":19.664344207229252,"none":25.413520858106526},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T04:39:46Z","match_totals_all":{"draws":794,"losses":1344,"wins":566},"match_totals_tracks":{"medium":{"draws":123,"losses":780,"wins":229},"none":{"draws":671,"losses":564,"wins":337}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":64.41021093686129,"mean":19.076433948411953,"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","below_generation_quality_threshold"],"overall_official_rank":70,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-02":{"draws":178,"losses":44,"wins":6},"GB2-03":{"draws":161,"losses":102,"wins":43},"GB2-04":{"draws":198,"losses":33,"wins":13},"GB2-05":{"draws":0,"losses":293,"wins":129},"GB2-06":{"draws":24,"losses":368,"wins":66},"GB2-07":{"draws":0,"losses":246,"wins":288},"GB2-08":{"draws":233,"losses":258,"wins":21}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":70,"losses":61,"wins":27},"GB2-05":{"draws":0,"losses":166,"wins":50},"GB2-06":{"draws":21,"losses":190,"wins":31},"GB2-07":{"draws":0,"losses":164,"wins":100},"GB2-08":{"draws":32,"losses":199,"wins":21}},"none":{"GB2-02":{"draws":178,"losses":44,"wins":6},"GB2-03":{"draws":91,"losses":41,"wins":16},"GB2-04":{"draws":198,"losses":33,"wins":13},"GB2-05":{"draws":0,"losses":127,"wins":79},"GB2-06":{"draws":3,"losses":178,"wins":35},"GB2-07":{"draws":0,"losses":82,"wins":188},"GB2-08":{"draws":201,"losses":59,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1356.425403755977,"GB2-05":1042.2355616023424,"GB2-06":1061.8649075082567,"GB2-07":1243.3874575327422,"GB2-08":1028.5534449140578},"none":{"GB2-02":1355.2935788876514,"GB2-03":1354.0923611256612,"GB2-04":1434.832200144136,"GB2-05":1292.5079376692024,"GB2-06":927.422935353858,"GB2-07":1758.8260987195004,"GB2-08":1313.1681070033744}},"per_game_tracks":{"medium":{"GB2-03":23.674987449563744,"GB2-05":20.33095894441932,"GB2-06":24.054947005452874,"GB2-07":30.260827636710317,"GB2-08":0.0},"none":{"GB2-02":0.2262091487934769,"GB2-03":23.35805782500073,"GB2-04":15.912339903851171,"GB2-05":36.030884861522324,"GB2-06":15.84758202107365,"GB2-07":64.41021093686129,"GB2-08":22.109361309643063}},"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":17.484349207816972,"none":20.668518689006937},"reasoning_agg":{"medium":{"max":30.260827636710317,"mean":17.484349207816972,"min":0.0},"none":{"max":64.41021093686129,"mean":20.668518689006937,"min":0.2262091487934769}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":64.41021093686129,"reasoning_variance":3.184169481189965},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":30.260827636710317,"expected_score":15.643327501636758,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.8410217061802143},"none":{"ceiling_score":64.41021093686129,"expected_score":24.479359551168983,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.8108408621620455}}},{"canonical_public_row_identity":"publication-row.v1:overall:inclusionai-ling-3-0-flash:4585443c22a6925f","codegen_cost_by_reasoning":{"medium":{"admitted_cell_count":6,"cell_count":8,"cost_basis_counts":{"provider_reported":52},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":21.696778199463118,"none":17.996848350092318},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":1894,"losses":2356,"wins":874},"match_totals_tracks":{"medium":{"draws":713,"losses":1309,"wins":544},"none":{"draws":1181,"losses":1047,"wins":330}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":38.8181251334053,"mean":16.628262521932577,"min":3.9673760156779903},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","unknown_capability_evidence","missing_generation_quality","below_generation_quality_threshold","fixed_coverage_incomplete"],"overall_official_rank":71,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":245,"losses":485,"wins":168},"GB2-02":{"draws":521,"losses":116,"wins":9},"GB2-03":{"draws":139,"losses":200,"wins":53},"GB2-04":{"draws":532,"losses":96,"wins":46},"GB2-06":{"draws":11,"losses":748,"wins":179},"GB2-07":{"draws":0,"losses":569,"wins":391},"GB2-08":{"draws":446,"losses":142,"wins":28}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":101,"losses":268,"wins":21},"GB2-02":{"draws":299,"losses":75,"wins":4},"GB2-04":{"draws":309,"losses":67,"wins":28},"GB2-06":{"draws":4,"losses":330,"wins":100},"GB2-07":{"draws":0,"losses":569,"wins":391}},"none":{"GB2-01":{"draws":144,"losses":217,"wins":147},"GB2-02":{"draws":222,"losses":41,"wins":5},"GB2-03":{"draws":139,"losses":200,"wins":53},"GB2-04":{"draws":223,"losses":29,"wins":18},"GB2-06":{"draws":7,"losses":418,"wins":79},"GB2-08":{"draws":446,"losses":142,"wins":28}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1233.0587794009825,"GB2-02":1414.568576939123,"GB2-04":1420.321014279498,"GB2-06":1204.6422026292603,"GB2-07":1388.486252734322},"none":{"GB2-01":1379.8496803976227,"GB2-02":1432.82362044447,"GB2-03":1239.5582299644625,"GB2-04":1425.090677777107,"GB2-06":858.1079828348421,"GB2-08":1315.0433872507501}},"per_game_tracks":{"medium":{"GB2-01":22.529468441589415,"GB2-02":3.9673760156779903,"GB2-04":11.317885539496896,"GB2-06":31.851035867145995,"GB2-07":38.8181251334053},"none":{"GB2-01":34.782123631421356,"GB2-02":11.374662755787572,"GB2-03":13.019426225888171,"GB2-04":14.610882549889865,"GB2-06":11.783681626492076,"GB2-08":22.410313311074873}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":17.25481261058409,"none":16.001712433281064},"reasoning_agg":{"medium":{"max":38.8181251334053,"mean":17.25481261058409,"min":3.9673760156779903},"none":{"max":34.782123631421356,"mean":16.001712433281064,"min":11.374662755787572}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":38.8181251334053,"reasoning_variance":1.2531001773030255},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":38.8181251334053,"expected_score":19.722828709000034,"reliability_score":77.82846544227553,"uncertainty_avg":22.17153455772447,"uncertainty_penalty":2.4680160984159443},"none":{"ceiling_score":34.782123631421356,"expected_score":17.957171913555843,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.9554594802747793}}},{"canonical_public_row_identity":"publication-row.v1:overall:google-gemini-3-1-flash-lite:01d4f61c18cd57c6","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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},"cost_is_complete":false,"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":0.04706874999999999},"historical-provider-setting-intensive":{"admitted_cell_count":5,"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":false,"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":0.21994024999999998}},"codegen_cost_usd":{"admitted_cell_count":16,"cell_count":24,"cost_basis_counts":{"provider_reported":50},"cost_is_complete":false,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.0422995,"mean":0.014503875,"median":0.010566625,"min":0.003432,"recorded_attempt_count":50,"run_count":24,"total":0.348093},"codegen_latency_ms":{"attempt_count":37,"max_ms":98448,"mean_ms":43627.1875,"min_ms":14244,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":19,"max_ms":98448,"mean_ms":63383.0,"min_ms":47134,"run_count":8},"medium":{"attempt_count":18,"max_ms":33720,"mean_ms":23871.375,"min_ms":14244,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":22966,"output_mean":9375.1875,"output_min":1329,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":19,"output_max":22966,"output_mean":14948.625,"output_min":10673,"run_count":8},"medium":{"attempt_count":18,"output_max":5938,"output_mean":3801.75,"output_min":1329,"run_count":8}},"display_name":"Gemini 3.1 Flash Lite","economics":{"all":18.489275601699536,"highest":19.996649120521248,"medium":19.973608748993396,"none":14.54091705000395},"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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","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":"2026-09-26T04:47:02Z","match_totals_all":{"draws":925,"losses":2054,"wins":634},"match_totals_tracks":{"highest":{"draws":318,"losses":631,"wins":196},"medium":{"draws":374,"losses":798,"wins":294},"none":{"draws":233,"losses":625,"wins":144}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":31.71880473883156,"mean":16.43208625085612,"min":0.8064494175958549},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":72,"overall_ranking_status":"partial","per_game":{"GB2-04":14.806553561122028,"GB2-05":14.52621246431368,"GB2-06":22.003475064496904,"GB2-07":28.73675906479361,"GB2-08":19.910245447880012},"per_game_all":{"GB2-05":16.978781026991733,"GB2-06":26.311518896001246,"GB2-07":12.177526882105633},"per_game_match_totals_all":{"GB2-01":{"draws":169,"losses":219,"wins":60},"GB2-02":{"draws":182,"losses":19,"wins":1},"GB2-04":{"draws":324,"losses":79,"wins":47},"GB2-05":{"draws":0,"losses":458,"wins":124},"GB2-06":{"draws":6,"losses":472,"wins":209},"GB2-07":{"draws":0,"losses":582,"wins":114},"GB2-08":{"draws":244,"losses":225,"wins":79}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":157,"losses":44,"wins":17},"GB2-05":{"draws":0,"losses":161,"wins":37},"GB2-06":{"draws":0,"losses":166,"wins":53},"GB2-07":{"draws":0,"losses":173,"wins":77},"GB2-08":{"draws":161,"losses":87,"wins":12}},"medium":{"GB2-01":{"draws":123,"losses":88,"wins":39},"GB2-04":{"draws":167,"losses":35,"wins":30},"GB2-05":{"draws":0,"losses":150,"wins":58},"GB2-06":{"draws":1,"losses":172,"wins":75},"GB2-07":{"draws":0,"losses":215,"wins":25},"GB2-08":{"draws":83,"losses":138,"wins":67}},"none":{"GB2-01":{"draws":46,"losses":131,"wins":21},"GB2-02":{"draws":182,"losses":19,"wins":1},"GB2-05":{"draws":0,"losses":147,"wins":29},"GB2-06":{"draws":5,"losses":134,"wins":81},"GB2-07":{"draws":0,"losses":194,"wins":12}}},"per_game_raw_elo_all":{"GB2-05":990.4797012048894,"GB2-06":1099.987669088767,"GB2-07":971.9998865219741},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1429.0975621767814,"GB2-05":951.14327166526,"GB2-06":1029.1950743346495,"GB2-07":1221.047472497891,"GB2-08":1284.8201706174598},"medium":{"GB2-01":1310.2844110489343,"GB2-04":1437.4950482284587,"GB2-05":1076.4838164036346,"GB2-06":1080.722317526352,"GB2-07":893.1444456237225,"GB2-08":1274.8321071010118},"none":{"GB2-01":1135.7474644714616,"GB2-02":1421.965157179802,"GB2-05":943.8120155457733,"GB2-06":1190.0456154053,"GB2-07":801.8077414443085}},"per_game_tracks":{"highest":{"GB2-04":14.806553561122028,"GB2-05":14.52621246431368,"GB2-06":22.003475064496904,"GB2-07":28.73675906479361,"GB2-08":19.910245447880012},"medium":{"GB2-01":29.735460219399265,"GB2-04":16.221116392593462,"GB2-05":22.452598379233287,"GB2-06":25.212276884675276,"GB2-07":6.989372163927432,"GB2-08":19.230828454131633},"none":{"GB2-01":16.884840426674792,"GB2-02":9.336958429489302,"GB2-05":13.95753223742823,"GB2-06":31.71880473883156,"GB2-07":0.8064494175958549}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":17.779814700397935,"medium":18.587537355617464,"none":12.928906696552968},"reasoning_agg":{"highest":{"max":28.73675906479361,"mean":17.779814700397935,"min":14.52621246431368},"medium":{"max":29.735460219399265,"mean":18.587537355617464,"min":6.989372163927432},"none":{"max":31.71880473883156,"mean":12.928906696552968,"min":0.8064494175958549}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":31.71880473883156,"expected_score":11.274627372016594,"reasoning_variance":5.658630659064496,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.157458878839526},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":28.73675906479361,"expected_score":6.690441799074824,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-11.089372901323111},"medium":{"ceiling_score":29.735460219399265,"expected_score":18.05669210879059,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.5308452468268747},"none":{"ceiling_score":31.71880473883156,"expected_score":13.461768399779249,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.5328617032262812}}},{"canonical_public_row_identity":"publication-row.v1:overall:ibm-granite-granite-4-2-8b:ebff985e112e2d67","codegen_cost_by_reasoning":{"highest":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.010999479999999999,"mean":0.007405580000000001,"median":0.00734207,"min":0.0037107299999999998,"recorded_attempt_count":17,"run_count":8,"total":0.05924464},"medium":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.00272269,"mean":0.001801155,"median":0.001648355,"min":0.00126116,"recorded_attempt_count":18,"run_count":8,"total":0.014409239999999999},"none":{"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.00394984,"mean":0.0028174899999999998,"median":0.00280168,"min":0.0021764799999999997,"recorded_attempt_count":19,"run_count":8,"total":0.022539919999999998}},"codegen_cost_by_setting":{"historical-provider-setting-balanced":{"admitted_cell_count":2,"cell_count":8,"cost_basis_counts":{"provider_reported":18},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":6,"max":0.00272269,"mean":0.001801155,"median":0.001648355,"min":0.00126116,"recorded_attempt_count":18,"run_count":8,"total":0.01440924},"historical-provider-setting-baseline":{"cell_count":8,"cost_basis_counts":{"provider_reported":19},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":8,"max":0.00394984,"mean":0.0028174899999999998,"median":0.00280168,"min":0.0021764799999999997,"recorded_attempt_count":19,"run_count":8,"total":0.022539919999999998},"historical-provider-setting-intensive":{"admitted_cell_count":1,"cell_count":8,"cost_basis_counts":{"provider_reported":17},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":7,"max":0.010999479999999999,"mean":0.007405580000000001,"median":0.00734207,"min":0.0037107299999999998,"recorded_attempt_count":17,"run_count":8,"total":0.05924464}},"codegen_cost_usd":{"admitted_cell_count":3,"cell_count":24,"cost_basis_counts":{"provider_reported":54},"cost_is_complete":true,"evidence_basis":"Provider-reported","failed_cell_count":21,"max":0.010999479999999999,"mean":0.004008075000000001,"median":0.00280168,"min":0.00126116,"recorded_attempt_count":54,"run_count":24,"total":0.0961938},"codegen_latency_ms":{"attempt_count":54,"max_ms":509048,"mean_ms":136775.45833333334,"min_ms":42240,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":17,"max_ms":509048,"mean_ms":269734.875,"min_ms":169447,"run_count":8},"medium":{"attempt_count":18,"max_ms":98606,"mean_ms":61749.125,"min_ms":42240,"run_count":8},"none":{"attempt_count":19,"max_ms":136274,"mean_ms":78842.375,"min_ms":49515,"run_count":8}},"codegen_output_tokens":{"attempt_count":54,"output_max":45556,"output_mean":12967.0,"output_min":2790,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":17,"output_max":45556,"output_mean":27869.5,"output_min":14641,"run_count":8},"medium":{"attempt_count":18,"output_max":6691,"output_mean":4472.75,"output_min":2790,"run_count":8},"none":{"attempt_count":19,"output_max":9484,"output_mean":6558.75,"output_min":4755,"run_count":8}},"display_name":"Granite 4.2 8B","economics":{"highest":22.495226500211192,"medium":10.909432569304167},"first_seen_at":null,"generation_metadata":{"attempt_evidence":{"finish_reason_observations":54,"finish_reasons":["stop"],"indexed_attempts":54,"output_token_observations":54,"provider_post_attempt_observations":54,"provider_post_attempts":54,"reasoning_token_observations":54,"reconciliation_get_attempt_observations":54,"reconciliation_get_attempts":257,"total_output_tokens":311208,"total_reasoning_output_tokens":196736,"total_visible_output_tokens":114472,"visible_token_observations":54},"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":"ibm-granite/granite-4.2-8b","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":"56b5362a34d35e3eed1e34ba33756ab052c47ef0bdb541049753d7f172fb7a71","reasoning_policy_version":"gb2_reasoning_brackets_v2","reasoning_request_mode":null,"requested_reasoning_effort":null}},"generation_quality_by_reasoning":{"balanced":{"admitted_plugins":2,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-03","GB2-04","GB2-05","GB2-06"],"model_code_failure_rate":0.75,"model_code_failures":6,"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":1,"evaluated_cells":8,"failed_game_aliases":["GB2-01","GB2-02","GB2-04","GB2-05","GB2-06","GB2-07","GB2-08"],"model_code_failure_rate":0.875,"model_code_failures":7,"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}},"id":"ibm-granite/granite-4.2-8b","is_recent_addition":false,"last_measured_at":"2026-09-26T01:33:33Z","match_totals_all":{"draws":381,"losses":413,"wins":18},"match_totals_tracks":{"highest":{"draws":182,"losses":68,"wins":6},"medium":{"draws":199,"losses":345,"wins":12}},"model_slug":"ibm-granite-granite-4-2-8b","overall":{"max":22.495226500211192,"mean":10.544937726238405,"min":1.1310681594006966},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality","below_generation_quality_threshold"],"overall_official_rank":73,"overall_ranking_status":"partial","per_game":{"GB2-03":22.495226500211192},"per_game_match_totals_all":{"GB2-03":{"draws":182,"losses":68,"wins":6},"GB2-07":{"draws":0,"losses":268,"wins":12},"GB2-08":{"draws":199,"losses":77,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":182,"losses":68,"wins":6}},"medium":{"GB2-07":{"draws":0,"losses":268,"wins":12},"GB2-08":{"draws":199,"losses":77,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1337.0717539024693},"medium":{"GB2-07":802.770098992688,"GB2-08":1294.1175734471324}},"per_game_tracks":{"highest":{"GB2-03":22.495226500211192},"medium":{"GB2-07":1.1310681594006966,"GB2-08":20.687796979207636}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":13.375741703824454,"medium":7.714133748652357},"reasoning_agg":{"highest":{"max":22.495226500211192,"mean":13.375741703824454,"min":22.495226500211192},"medium":{"max":20.687796979207636,"mean":7.714133748652357,"min":1.1310681594006966}},"reasoning_labels":{"highest":"Full","medium":"Low","none":"Setting not tested"},"reasoning_settings":{"balanced":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":22.495226500211192,"reasoning_variance":5.661607955172097},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":22.495226500211192,"expected_score":5.577688246104671,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.798053457719783},"medium":{"ceiling_score":20.687796979207636,"expected_score":11.767091399353529,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.052957650701171}}}],"public_release_id":"gb2-20260926-80fec42d483b","results_cut_id":"gb2-20260926-80fec42d483b","schema_version":2,"snapshot_id":"20260926_085516","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-09-26 08:55 UTC","versus_totals_all":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":36,"wins":36},"claude-fable-5":{"draws":22,"losses":54,"wins":16},"claude-fable-5-1":{"draws":4,"losses":86,"wins":4},"claude-opus-4-5":{"draws":43,"losses":70,"wins":29},"claude-opus-4-8":{"draws":6,"losses":10,"wins":8},"claude-opus-5":{"draws":7,"losses":46,"wins":11},"claude-opus-5-5":{"draws":0,"losses":12,"wins":2},"claude-sonnet-5":{"draws":46,"losses":72,"wins":24},"cohere/north-mini-code":{"draws":7,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":49,"losses":60,"wins":33},"deepseek/deepseek-v4-pro":{"draws":38,"losses":61,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":50,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":10,"wins":6},"google/gemini-3.1-flash-lite":{"draws":11,"losses":7,"wins":18},"google/gemini-3.5-flash":{"draws":41,"losses":56,"wins":29},"google/gemini-3.5-flash-lite":{"draws":90,"losses":79,"wins":87},"google/gemini-3.6-flash":{"draws":60,"losses":89,"wins":51},"google/gemini-3.8-flash":{"draws":33,"losses":56,"wins":21},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":4,"wins":0},"gpt-5":{"draws":10,"losses":17,"wins":13},"gpt-5.4":{"draws":30,"losses":33,"wins":25},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":10,"losses":13,"wins":11},"gpt-5.5":{"draws":22,"losses":16,"wins":10},"gpt-5.6-luna":{"draws":50,"losses":42,"wins":52},"gpt-5.6-sol":{"draws":14,"losses":68,"wins":16},"gpt-5.6-terra":{"draws":40,"losses":56,"wins":24},"gpt-6-astra":{"draws":5,"losses":59,"wins":10},"gpt-6-luna":{"draws":1,"losses":5,"wins":10},"gpt-6-sol":{"draws":0,"losses":13,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":13},"inception/mercury-2.5-preview":{"draws":48,"losses":29,"wins":35},"inclusionai/ling-3.0-flash":{"draws":27,"losses":9,"wins":20},"meituan/longcat-2.0":{"draws":30,"losses":21,"wins":31},"meta/muse-glimmer-30b":{"draws":59,"losses":36,"wins":47},"meta/muse-spark-1.2":{"draws":25,"losses":31,"wins":24},"meta/muse-spark-1.3":{"draws":23,"losses":50,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":9,"wins":21},"mistralai/mistral-medium-3-5":{"draws":38,"losses":19,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":29,"losses":46,"wins":21},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":13,"wins":17},"o3":{"draws":24,"losses":69,"wins":43},"openai/gpt-oss-120b":{"draws":52,"losses":39,"wins":43},"poolside/laguna-s-2.1":{"draws":43,"losses":23,"wins":30},"qwen/qwen3.7-max":{"draws":7,"losses":13,"wins":12},"qwen/qwen3.7-plus":{"draws":9,"losses":2,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":44,"losses":44,"wins":28},"qwen/qwen3.8-27b":{"draws":14,"losses":36,"wins":22},"qwen/qwen3.8-flash":{"draws":36,"losses":35,"wins":19},"qwen/qwen3.8-max":{"draws":49,"losses":47,"wins":44},"qwen/qwen3.8-max-0902":{"draws":7,"losses":12,"wins":3},"stealth/ox-alpha":{"draws":99,"losses":194,"wins":87},"stepfun/step-3.7-flash":{"draws":4,"losses":14,"wins":20},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":47,"losses":68,"wins":21},"thinkingmachines/inkling":{"draws":40,"losses":35,"wins":57},"thinkingmachines/inkling-small":{"draws":58,"losses":27,"wins":55},"x-ai/grok-4.5":{"draws":31,"losses":57,"wins":14},"x-ai/grok-4.6":{"draws":35,"losses":50,"wins":19},"x-ai/grok-4.7":{"draws":0,"losses":8,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":11,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":11,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":14,"wins":7},"z-ai/glm-5.2":{"draws":78,"losses":49,"wins":55},"z-ai/glm-5.3":{"draws":25,"losses":58,"wins":13},"z-ai/glm-5.3-flash":{"draws":35,"losses":53,"wins":16},"z-ai/glm-5.3-flashx":{"draws":3,"losses":15,"wins":2}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":16,"wins":54},"claude-fable-5":{"draws":12,"losses":42,"wins":42},"claude-fable-5-1":{"draws":5,"losses":137,"wins":28},"claude-opus-4-5":{"draws":25,"losses":16,"wins":101},"claude-opus-4-8":{"draws":7,"losses":11,"wins":16},"claude-opus-5":{"draws":11,"losses":80,"wins":27},"claude-opus-5-5":{"draws":3,"losses":15,"wins":2},"claude-sonnet-5":{"draws":35,"losses":24,"wins":85},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":29,"losses":13,"wins":90},"deepseek/deepseek-v4-pro":{"draws":25,"losses":34,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":20,"wins":71},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":10},"google/gemini-3.5-flash":{"draws":31,"losses":30,"wins":93},"google/gemini-3.5-flash-lite":{"draws":44,"losses":31,"wins":137},"google/gemini-3.6-flash":{"draws":39,"losses":66,"wins":105},"google/gemini-3.8-flash":{"draws":25,"losses":51,"wins":70},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":11},"gpt-4.1":{"draws":0,"losses":4,"wins":4},"gpt-5":{"draws":11,"losses":10,"wins":21},"gpt-5.4":{"draws":37,"losses":47,"wins":60},"gpt-5.4-mini":{"draws":9,"losses":3,"wins":14},"gpt-5.4-nano":{"draws":3,"losses":7,"wins":28},"gpt-5.5":{"draws":7,"losses":11,"wins":18},"gpt-5.6-luna":{"draws":32,"losses":20,"wins":52},"gpt-5.6-sol":{"draws":21,"losses":70,"wins":73},"gpt-5.6-terra":{"draws":39,"losses":23,"wins":88},"gpt-6-astra":{"draws":12,"losses":119,"wins":33},"gpt-6-luna":{"draws":5,"losses":2,"wins":11},"gpt-6-sol":{"draws":5,"losses":12,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":24,"losses":3,"wins":37},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":18},"meituan/longcat-2.0":{"draws":11,"losses":22,"wins":42},"meta/muse-glimmer-30b":{"draws":28,"losses":8,"wins":38},"meta/muse-spark-1.2":{"draws":18,"losses":27,"wins":47},"meta/muse-spark-1.3":{"draws":20,"losses":43,"wins":65},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":15},"mistralai/mistral-medium-3-5":{"draws":24,"losses":8,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":26,"losses":20,"wins":84},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":21},"o3":{"draws":11,"losses":20,"wins":105},"openai/gpt-oss-120b":{"draws":28,"losses":11,"wins":53},"poolside/laguna-s-2.1":{"draws":22,"losses":12,"wins":44},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":13},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":39,"wins":63},"qwen/qwen3.8-27b":{"draws":10,"losses":17,"wins":43},"qwen/qwen3.8-flash":{"draws":30,"losses":13,"wins":45},"qwen/qwen3.8-max":{"draws":21,"losses":41,"wins":72},"qwen/qwen3.8-max-0902":{"draws":8,"losses":4,"wins":14},"stealth/ox-alpha":{"draws":103,"losses":104,"wins":267},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":33},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":14},"tencent/hy4-preview":{"draws":25,"losses":30,"wins":83},"thinkingmachines/inkling":{"draws":18,"losses":2,"wins":58},"thinkingmachines/inkling-small":{"draws":30,"losses":12,"wins":62},"x-ai/grok-4.5":{"draws":16,"losses":41,"wins":55},"x-ai/grok-4.6":{"draws":39,"losses":56,"wins":75},"x-ai/grok-4.7":{"draws":1,"losses":13,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":6,"wins":12},"xiaomi/mimo-v2.5":{"draws":13,"losses":2,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":3,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":5,"wins":16},"z-ai/glm-5.2":{"draws":47,"losses":29,"wins":78},"z-ai/glm-5.3":{"draws":22,"losses":77,"wins":55},"z-ai/glm-5.3-flash":{"draws":27,"losses":45,"wins":76},"z-ai/glm-5.3-flashx":{"draws":6,"losses":11,"wins":11}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":4,"wins":86},"claude-fable-5":{"draws":5,"losses":28,"wins":137},"claude-fable-5-1":{"draws":10,"losses":85,"wins":85},"claude-opus-4-5":{"draws":6,"losses":3,"wins":145},"claude-opus-4-8":{"draws":2,"losses":5,"wins":23},"claude-opus-5":{"draws":10,"losses":27,"wins":37},"claude-opus-5-5":{"draws":5,"losses":18,"wins":15},"claude-sonnet-5":{"draws":11,"losses":5,"wins":158},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":6,"losses":1,"wins":115},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":117},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":4,"wins":124},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":5,"wins":37},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":28},"google/gemini-3.5-flash":{"draws":14,"losses":10,"wins":138},"google/gemini-3.5-flash-lite":{"draws":16,"losses":1,"wins":169},"google/gemini-3.6-flash":{"draws":12,"losses":23,"wins":193},"google/gemini-3.8-flash":{"draws":15,"losses":15,"wins":148},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":16},"gpt-4.1":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":1,"wins":44},"gpt-5.4":{"draws":12,"losses":20,"wins":124},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":20},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":22},"gpt-5.5":{"draws":4,"losses":5,"wins":35},"gpt-5.6-luna":{"draws":10,"losses":4,"wins":82},"gpt-5.6-sol":{"draws":17,"losses":27,"wins":144},"gpt-5.6-terra":{"draws":13,"losses":3,"wins":126},"gpt-6-astra":{"draws":18,"losses":110,"wins":66},"gpt-6-luna":{"draws":1,"losses":0,"wins":17},"gpt-6-sol":{"draws":0,"losses":8,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":5,"losses":0,"wins":39},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":38},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":50},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":60},"meta/muse-spark-1.2":{"draws":10,"losses":9,"wins":95},"meta/muse-spark-1.3":{"draws":4,"losses":7,"wins":127},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":20},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":14,"losses":4,"wins":130},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":38},"o3":{"draws":0,"losses":6,"wins":118},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":62},"poolside/laguna-s-2.1":{"draws":5,"losses":0,"wins":71},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":8,"wins":135},"qwen/qwen3.8-27b":{"draws":3,"losses":1,"wins":70},"qwen/qwen3.8-flash":{"draws":5,"losses":4,"wins":83},"qwen/qwen3.8-max":{"draws":6,"losses":5,"wins":139},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":25},"stealth/ox-alpha":{"draws":52,"losses":27,"wins":475},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":20},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":28},"tencent/hy4-preview":{"draws":6,"losses":14,"wins":128},"thinkingmachines/inkling":{"draws":7,"losses":0,"wins":75},"thinkingmachines/inkling-small":{"draws":8,"losses":1,"wins":109},"x-ai/grok-4.5":{"draws":1,"losses":10,"wins":97},"x-ai/grok-4.6":{"draws":11,"losses":24,"wins":147},"x-ai/grok-4.7":{"draws":1,"losses":1,"wins":16},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":18},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":66},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":5,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":13},"z-ai/glm-5.2":{"draws":18,"losses":3,"wins":107},"z-ai/glm-5.3":{"draws":10,"losses":30,"wins":130},"z-ai/glm-5.3-flash":{"draws":16,"losses":17,"wins":135},"z-ai/glm-5.3-flashx":{"draws":4,"losses":4,"wins":36}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":21,"wins":60},"claude-fable-5":{"draws":23,"losses":84,"wins":15},"claude-fable-5-1":{"draws":5,"losses":130,"wins":3},"claude-opus-4-5":{"draws":59,"losses":50,"wins":61},"claude-opus-4-8":{"draws":32,"losses":65,"wins":29},"claude-opus-5":{"draws":37,"losses":193,"wins":26},"claude-opus-5-5":{"draws":5,"losses":29,"wins":2},"claude-sonnet-5":{"draws":71,"losses":43,"wins":104},"cohere/north-mini-code":{"draws":8,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":35,"losses":35,"wins":66},"deepseek/deepseek-v4-pro":{"draws":22,"losses":36,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":43,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":18,"wins":0},"google/gemini-3.1-flash-lite":{"draws":19,"losses":5,"wins":50},"google/gemini-3.5-flash":{"draws":32,"losses":58,"wins":44},"google/gemini-3.5-flash-lite":{"draws":156,"losses":105,"wins":217},"google/gemini-3.6-flash":{"draws":109,"losses":192,"wins":147},"google/gemini-3.8-flash":{"draws":30,"losses":63,"wins":25},"google/gemma-4-31b-it":{"draws":14,"losses":15,"wins":25},"gpt-4.1":{"draws":19,"losses":10,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":6},"gpt-5":{"draws":28,"losses":16,"wins":20},"gpt-5.4":{"draws":52,"losses":104,"wins":38},"gpt-5.4-mini":{"draws":36,"losses":20,"wins":26},"gpt-5.4-nano":{"draws":27,"losses":32,"wins":59},"gpt-5.5":{"draws":49,"losses":41,"wins":18},"gpt-5.6-luna":{"draws":70,"losses":51,"wins":77},"gpt-5.6-sol":{"draws":36,"losses":156,"wins":42},"gpt-5.6-terra":{"draws":38,"losses":21,"wins":41},"gpt-6-astra":{"draws":10,"losses":110,"wins":6},"gpt-6-luna":{"draws":11,"losses":6,"wins":11},"gpt-6-sol":{"draws":5,"losses":21,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":32,"losses":7,"wins":43},"inclusionai/ling-3.0-flash":{"draws":30,"losses":16,"wins":44},"meituan/longcat-2.0":{"draws":47,"losses":34,"wins":96},"meta/muse-glimmer-30b":{"draws":28,"losses":13,"wins":49},"meta/muse-spark-1.2":{"draws":37,"losses":69,"wins":42},"meta/muse-spark-1.3":{"draws":18,"losses":54,"wins":26},"minimax/minimax-m3":{"draws":18,"losses":9,"wins":25},"mistralai/mistral-medium-3-5":{"draws":15,"losses":8,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":10,"wins":19},"moonshotai/kimi-k3":{"draws":92,"losses":87,"wins":61},"nex-agi/nex-n2-pro":{"draws":13,"losses":9,"wins":32},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":15,"wins":41},"o3":{"draws":44,"losses":89,"wins":195},"openai/gpt-oss-120b":{"draws":19,"losses":7,"wins":52},"poolside/laguna-s-2.1":{"draws":78,"losses":15,"wins":79},"qwen/qwen3.7-max":{"draws":18,"losses":16,"wins":30},"qwen/qwen3.7-plus":{"draws":15,"losses":12,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":46,"losses":44,"wins":38},"qwen/qwen3.8-27b":{"draws":15,"losses":21,"wins":28},"qwen/qwen3.8-flash":{"draws":26,"losses":26,"wins":26},"qwen/qwen3.8-max":{"draws":39,"losses":61,"wins":31},"qwen/qwen3.8-max-0902":{"draws":4,"losses":9,"wins":1},"stealth/ox-alpha":{"draws":117,"losses":155,"wins":119},"stepfun/step-3.7-flash":{"draws":20,"losses":15,"wins":55},"tencent/hy3-preview":{"draws":23,"losses":16,"wins":25},"tencent/hy4-preview":{"draws":30,"losses":52,"wins":36},"thinkingmachines/inkling":{"draws":65,"losses":30,"wins":109},"thinkingmachines/inkling-small":{"draws":34,"losses":17,"wins":58},"x-ai/grok-4.5":{"draws":82,"losses":106,"wins":66},"x-ai/grok-4.6":{"draws":34,"losses":64,"wins":18},"x-ai/grok-4.7":{"draws":2,"losses":8,"wins":4},"x-ai/grok-build-0.1":{"draws":18,"losses":3,"wins":21},"xiaomi/mimo-v2.5":{"draws":53,"losses":30,"wins":77},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":34,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":3,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":58,"losses":50,"wins":96},"z-ai/glm-5.3":{"draws":29,"losses":74,"wins":17},"z-ai/glm-5.3-flash":{"draws":28,"losses":53,"wins":37},"z-ai/glm-5.3-flashx":{"draws":3,"losses":5,"wins":0}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":8,"wins":10},"claude-fable-5":{"draws":7,"losses":16,"wins":11},"claude-fable-5-1":{"draws":2,"losses":23,"wins":5},"claude-opus-4-5":{"draws":50,"losses":45,"wins":113},"claude-opus-4-8":{"draws":24,"losses":38,"wins":38},"claude-opus-5":{"draws":50,"losses":156,"wins":54},"claude-opus-5-5":{"draws":0,"losses":27,"wins":3},"claude-sonnet-5":{"draws":11,"losses":6,"wins":13},"cohere/north-mini-code":{"draws":14,"losses":4,"wins":56},"deepseek/deepseek-v4-flash":{"draws":35,"losses":4,"wins":49},"deepseek/deepseek-v4-pro":{"draws":8,"losses":15,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":16,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":8,"wins":9},"google/gemini-3.1-flash-lite":{"draws":25,"losses":5,"wins":68},"google/gemini-3.5-flash":{"draws":34,"losses":12,"wins":34},"google/gemini-3.5-flash-lite":{"draws":36,"losses":16,"wins":56},"google/gemini-3.6-flash":{"draws":34,"losses":59,"wins":49},"google/gemini-3.8-flash":{"draws":6,"losses":15,"wins":17},"google/gemma-4-31b-it":{"draws":29,"losses":5,"wins":38},"gpt-4.1":{"draws":19,"losses":7,"wins":24},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":23,"losses":27,"wins":56},"gpt-5.4":{"draws":5,"losses":10,"wins":13},"gpt-5.4-mini":{"draws":28,"losses":29,"wins":43},"gpt-5.4-nano":{"draws":35,"losses":35,"wins":86},"gpt-5.5":{"draws":42,"losses":60,"wins":40},"gpt-5.6-luna":{"draws":9,"losses":4,"wins":17},"gpt-5.6-sol":{"draws":20,"losses":17,"wins":15},"gpt-5.6-terra":{"draws":11,"losses":7,"wins":26},"gpt-6-astra":{"draws":6,"losses":43,"wins":1},"gpt-6-luna":{"draws":2,"losses":4,"wins":6},"gpt-6-sol":{"draws":2,"losses":5,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":4,"wins":18},"inclusionai/ling-3.0-flash":{"draws":37,"losses":0,"wins":29},"meituan/longcat-2.0":{"draws":15,"losses":19,"wins":40},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":16},"meta/muse-spark-1.2":{"draws":14,"losses":11,"wins":23},"meta/muse-spark-1.3":{"draws":9,"losses":14,"wins":15},"minimax/minimax-m3":{"draws":22,"losses":12,"wins":44},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":9,"wins":15},"moonshotai/kimi-k3":{"draws":19,"losses":29,"wins":18},"nex-agi/nex-n2-pro":{"draws":31,"losses":8,"wins":39},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":15,"wins":70},"o3":{"draws":11,"losses":25,"wins":72},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":26,"losses":11,"wins":51},"qwen/qwen3.7-max":{"draws":28,"losses":21,"wins":39},"qwen/qwen3.7-plus":{"draws":15,"losses":16,"wins":43},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":11,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":11},"qwen/qwen3.8-max":{"draws":14,"losses":18,"wins":22},"qwen/qwen3.8-max-0902":{"draws":10,"losses":11,"wins":3},"stealth/ox-alpha":{"draws":36,"losses":61,"wins":37},"stepfun/step-3.7-flash":{"draws":16,"losses":14,"wins":42},"tencent/hy3-preview":{"draws":25,"losses":14,"wins":31},"tencent/hy4-preview":{"draws":14,"losses":27,"wins":19},"thinkingmachines/inkling":{"draws":24,"losses":17,"wins":67},"thinkingmachines/inkling-small":{"draws":10,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":28,"losses":43,"wins":37},"x-ai/grok-4.6":{"draws":8,"losses":19,"wins":17},"x-ai/grok-4.7":{"draws":4,"losses":8,"wins":6},"x-ai/grok-build-0.1":{"draws":18,"losses":10,"wins":32},"xiaomi/mimo-v2.5":{"draws":69,"losses":21,"wins":118},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":24,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":10,"wins":8},"z-ai/glm-5.2":{"draws":68,"losses":53,"wins":91},"z-ai/glm-5.3":{"draws":11,"losses":20,"wins":11},"z-ai/glm-5.3-flash":{"draws":8,"losses":16,"wins":14},"z-ai/glm-5.3-flashx":{"draws":4,"losses":7,"wins":9}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":11,"wins":46},"claude-fable-5":{"draws":11,"losses":27,"wins":80},"claude-fable-5-1":{"draws":10,"losses":37,"wins":27},"claude-opus-4-5":{"draws":60,"losses":50,"wins":306},"claude-opus-4-8":{"draws":50,"losses":54,"wins":156},"claude-opus-5":{"draws":82,"losses":291,"wins":291},"claude-opus-5-5":{"draws":4,"losses":27,"wins":11},"claude-sonnet-5":{"draws":11,"losses":18,"wins":53},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":45},"deepseek/deepseek-v4-flash":{"draws":19,"losses":10,"wins":107},"deepseek/deepseek-v4-pro":{"draws":5,"losses":6,"wins":49},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":9,"wins":19},"google/gemini-3.1-flash-lite":{"draws":19,"losses":4,"wins":69},"google/gemini-3.5-flash":{"draws":16,"losses":14,"wins":98},"google/gemini-3.5-flash-lite":{"draws":31,"losses":20,"wins":201},"google/gemini-3.6-flash":{"draws":39,"losses":50,"wins":189},"google/gemini-3.8-flash":{"draws":17,"losses":28,"wins":71},"google/gemma-4-31b-it":{"draws":14,"losses":11,"wins":59},"gpt-4.1":{"draws":12,"losses":7,"wins":70},"gpt-4.1-nano":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":24,"losses":14,"wins":144},"gpt-5.4":{"draws":5,"losses":6,"wins":55},"gpt-5.4-mini":{"draws":27,"losses":10,"wins":85},"gpt-5.4-nano":{"draws":26,"losses":24,"wins":162},"gpt-5.5":{"draws":35,"losses":78,"wins":169},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":62},"gpt-5.6-sol":{"draws":15,"losses":15,"wins":80},"gpt-5.6-terra":{"draws":11,"losses":3,"wins":50},"gpt-6-astra":{"draws":10,"losses":51,"wins":19},"gpt-6-luna":{"draws":6,"losses":1,"wins":29},"gpt-6-sol":{"draws":7,"losses":16,"wins":21},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":9,"losses":1,"wins":32},"inclusionai/ling-3.0-flash":{"draws":25,"losses":5,"wins":66},"meituan/longcat-2.0":{"draws":20,"losses":20,"wins":152},"meta/muse-glimmer-30b":{"draws":5,"losses":6,"wins":35},"meta/muse-spark-1.2":{"draws":4,"losses":12,"wins":40},"meta/muse-spark-1.3":{"draws":16,"losses":14,"wins":66},"minimax/minimax-m3":{"draws":12,"losses":10,"wins":86},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":25},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":2,"wins":66},"moonshotai/kimi-k3":{"draws":22,"losses":26,"wins":114},"nex-agi/nex-n2-pro":{"draws":1,"losses":6,"wins":57},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":3,"wins":121},"o3":{"draws":4,"losses":9,"wins":159},"openai/gpt-oss-120b":{"draws":10,"losses":0,"wins":52},"poolside/laguna-s-2.1":{"draws":17,"losses":16,"wins":181},"qwen/qwen3.7-max":{"draws":17,"losses":18,"wins":107},"qwen/qwen3.7-plus":{"draws":14,"losses":10,"wins":44},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":17,"wins":60},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":27},"qwen/qwen3.8-flash":{"draws":12,"losses":3,"wins":41},"qwen/qwen3.8-max":{"draws":12,"losses":10,"wins":54},"qwen/qwen3.8-max-0902":{"draws":9,"losses":12,"wins":21},"stealth/ox-alpha":{"draws":37,"losses":37,"wins":207},"stepfun/step-3.7-flash":{"draws":11,"losses":1,"wins":74},"tencent/hy3-preview":{"draws":22,"losses":11,"wins":95},"tencent/hy4-preview":{"draws":9,"losses":10,"wins":63},"thinkingmachines/inkling":{"draws":15,"losses":21,"wins":148},"thinkingmachines/inkling-small":{"draws":4,"losses":4,"wins":48},"x-ai/grok-4.5":{"draws":33,"losses":45,"wins":150},"x-ai/grok-4.6":{"draws":11,"losses":17,"wins":59},"x-ai/grok-4.7":{"draws":4,"losses":8,"wins":14},"x-ai/grok-build-0.1":{"draws":10,"losses":5,"wins":41},"xiaomi/mimo-v2.5":{"draws":48,"losses":16,"wins":202},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":6,"wins":82},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":5,"wins":6},"z-ai/glm-5.2":{"draws":53,"losses":25,"wins":182},"z-ai/glm-5.3":{"draws":15,"losses":20,"wins":49},"z-ai/glm-5.3-flash":{"draws":8,"losses":20,"wins":78},"z-ai/glm-5.3-flashx":{"draws":6,"losses":6,"wins":24}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":12},"claude-fable-5":{"draws":3,"losses":2,"wins":15},"claude-fable-5-1":{"draws":5,"losses":15,"wins":18},"claude-opus-4-5":{"draws":5,"losses":3,"wins":42},"claude-opus-4-8":{"draws":0,"losses":3,"wins":27},"claude-opus-5":{"draws":4,"losses":11,"wins":27},"claude-opus-5-5":{"draws":8,"losses":58,"wins":58},"claude-sonnet-5":{"draws":1,"losses":2,"wins":13},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":21},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":25},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":39},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":1,"losses":3,"wins":32},"google/gemini-3.5-flash-lite":{"draws":5,"losses":0,"wins":33},"google/gemini-3.6-flash":{"draws":4,"losses":2,"wins":40},"google/gemini-3.8-flash":{"draws":4,"losses":3,"wins":21},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":10},"gpt-4.1":{"draws":0,"losses":0,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":16},"gpt-5.4":{"draws":2,"losses":3,"wins":19},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":18},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":22},"gpt-5.5":{"draws":0,"losses":4,"wins":14},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":11},"gpt-5.6-sol":{"draws":1,"losses":2,"wins":19},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":22},"gpt-6-astra":{"draws":2,"losses":15,"wins":11},"gpt-6-luna":{"draws":16,"losses":1,"wins":133},"gpt-6-sol":{"draws":13,"losses":39,"wins":104},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":18},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":20},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":19},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":28},"meta/muse-spark-1.2":{"draws":0,"losses":2,"wins":12},"meta/muse-spark-1.3":{"draws":2,"losses":2,"wins":18},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":15},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":1,"losses":6,"wins":19},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":28},"o3":{"draws":1,"losses":2,"wins":29},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":37},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":30},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":22},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":14},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":18},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":16},"qwen/qwen3.8-max":{"draws":5,"losses":0,"wins":33},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":31},"stealth/ox-alpha":{"draws":11,"losses":5,"wins":88},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":24},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":22},"tencent/hy4-preview":{"draws":0,"losses":3,"wins":15},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":32},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":20},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":37},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":28},"x-ai/grok-4.7":{"draws":6,"losses":19,"wins":65},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":1,"wins":54},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":11,"wins":50},"z-ai/glm-5.2":{"draws":3,"losses":2,"wins":53},"z-ai/glm-5.3":{"draws":1,"losses":4,"wins":21},"z-ai/glm-5.3-flash":{"draws":7,"losses":1,"wins":28},"z-ai/glm-5.3-flashx":{"draws":14,"losses":8,"wins":96}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":46,"losses":24,"wins":72},"claude-fable-5":{"draws":35,"losses":85,"wins":24},"claude-fable-5-1":{"draws":11,"losses":158,"wins":5},"claude-opus-4-5":{"draws":79,"losses":112,"wins":57},"claude-opus-4-8":{"draws":11,"losses":13,"wins":6},"claude-opus-5":{"draws":11,"losses":53,"wins":18},"claude-opus-5-5":{"draws":1,"losses":13,"wins":2},"claude-sonnet-5":{"draws":56,"losses":72,"wins":72},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":64,"losses":36,"wins":78},"deepseek/deepseek-v4-pro":{"draws":48,"losses":44,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":42,"losses":53,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":9,"wins":5},"google/gemini-3.1-flash-lite":{"draws":14,"losses":3,"wins":27},"google/gemini-3.5-flash":{"draws":51,"losses":61,"wins":46},"google/gemini-3.5-flash-lite":{"draws":145,"losses":118,"wins":261},"google/gemini-3.6-flash":{"draws":112,"losses":189,"wins":147},"google/gemini-3.8-flash":{"draws":38,"losses":71,"wins":37},"google/gemma-4-31b-it":{"draws":8,"losses":3,"wins":13},"gpt-4.1":{"draws":3,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":5,"wins":7},"gpt-5":{"draws":13,"losses":10,"wins":9},"gpt-5.4":{"draws":83,"losses":152,"wins":51},"gpt-5.4-mini":{"draws":10,"losses":9,"wins":11},"gpt-5.4-nano":{"draws":6,"losses":14,"wins":12},"gpt-5.5":{"draws":13,"losses":20,"wins":3},"gpt-5.6-luna":{"draws":99,"losses":80,"wins":115},"gpt-5.6-sol":{"draws":49,"losses":237,"wins":43},"gpt-5.6-terra":{"draws":49,"losses":53,"wins":40},"gpt-6-astra":{"draws":7,"losses":131,"wins":10},"gpt-6-luna":{"draws":2,"losses":6,"wins":6},"gpt-6-sol":{"draws":3,"losses":31,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":12},"inception/mercury-2.5-preview":{"draws":51,"losses":9,"wins":52},"inclusionai/ling-3.0-flash":{"draws":28,"losses":12,"wins":66},"meituan/longcat-2.0":{"draws":53,"losses":17,"wins":88},"meta/muse-glimmer-30b":{"draws":49,"losses":18,"wins":59},"meta/muse-spark-1.2":{"draws":63,"losses":74,"wins":75},"meta/muse-spark-1.3":{"draws":48,"losses":50,"wins":34},"minimax/minimax-m3":{"draws":3,"losses":4,"wins":15},"mistralai/mistral-medium-3-5":{"draws":40,"losses":13,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":87,"losses":114,"wins":59},"nex-agi/nex-n2-pro":{"draws":9,"losses":4,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":10,"wins":19},"o3":{"draws":26,"losses":135,"wins":153},"openai/gpt-oss-120b":{"draws":54,"losses":20,"wins":74},"poolside/laguna-s-2.1":{"draws":55,"losses":11,"wins":86},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":20},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":61,"losses":51,"wins":36},"qwen/qwen3.8-27b":{"draws":20,"losses":25,"wins":31},"qwen/qwen3.8-flash":{"draws":31,"losses":27,"wins":36},"qwen/qwen3.8-max":{"draws":40,"losses":61,"wins":46},"qwen/qwen3.8-max-0902":{"draws":10,"losses":8,"wins":2},"stealth/ox-alpha":{"draws":121,"losses":206,"wins":142},"stepfun/step-3.7-flash":{"draws":9,"losses":21,"wins":32},"tencent/hy3-preview":{"draws":15,"losses":9,"wins":16},"tencent/hy4-preview":{"draws":48,"losses":59,"wins":35},"thinkingmachines/inkling":{"draws":64,"losses":26,"wins":110},"thinkingmachines/inkling-small":{"draws":49,"losses":26,"wins":87},"x-ai/grok-4.5":{"draws":69,"losses":99,"wins":42},"x-ai/grok-4.6":{"draws":43,"losses":68,"wins":37},"x-ai/grok-4.7":{"draws":2,"losses":12,"wins":4},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":26,"losses":2,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":14,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":10,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":8,"wins":5},"z-ai/glm-5.2":{"draws":64,"losses":54,"wins":78},"z-ai/glm-5.3":{"draws":27,"losses":105,"wins":16},"z-ai/glm-5.3-flash":{"draws":32,"losses":77,"wins":37},"z-ai/glm-5.3-flashx":{"draws":11,"losses":3,"wins":8}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":4,"wins":7},"claude-fable-5":{"draws":2,"losses":16,"wins":0},"claude-fable-5-1":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":13,"losses":46,"wins":11},"claude-opus-4-8":{"draws":14,"losses":56,"wins":4},"claude-opus-5":{"draws":6,"losses":45,"wins":5},"claude-opus-5-5":{"draws":1,"losses":21,"wins":0},"claude-sonnet-5":{"draws":1,"losses":9,"wins":2},"cohere/north-mini-code":{"draws":6,"losses":13,"wins":13},"deepseek/deepseek-v4-flash":{"draws":23,"losses":22,"wins":17},"deepseek/deepseek-v4-pro":{"draws":6,"losses":10,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":18,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":18,"wins":2},"google/gemini-3.1-flash-lite":{"draws":15,"losses":27,"wins":32},"google/gemini-3.5-flash":{"draws":12,"losses":17,"wins":7},"google/gemini-3.5-flash-lite":{"draws":35,"losses":14,"wins":13},"google/gemini-3.6-flash":{"draws":27,"losses":51,"wins":12},"google/gemini-3.8-flash":{"draws":2,"losses":10,"wins":6},"google/gemma-4-31b-it":{"draws":11,"losses":17,"wins":10},"gpt-4.1":{"draws":9,"losses":17,"wins":4},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":18,"losses":30,"wins":12},"gpt-5.4":{"draws":3,"losses":9,"wins":0},"gpt-5.4-mini":{"draws":20,"losses":23,"wins":7},"gpt-5.4-nano":{"draws":24,"losses":43,"wins":21},"gpt-5.5":{"draws":25,"losses":24,"wins":7},"gpt-5.6-luna":{"draws":3,"losses":11,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":13,"wins":2},"gpt-5.6-terra":{"draws":4,"losses":26,"wins":4},"gpt-6-astra":{"draws":0,"losses":16,"wins":0},"gpt-6-luna":{"draws":1,"losses":8,"wins":1},"gpt-6-sol":{"draws":3,"losses":8,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":12,"wins":10},"inclusionai/ling-3.0-flash":{"draws":29,"losses":20,"wins":9},"meituan/longcat-2.0":{"draws":35,"losses":33,"wins":8},"meta/muse-glimmer-30b":{"draws":2,"losses":16,"wins":4},"meta/muse-spark-1.2":{"draws":1,"losses":23,"wins":6},"meta/muse-spark-1.3":{"draws":0,"losses":12,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":33,"wins":15},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":11,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":18,"wins":4},"nex-agi/nex-n2-pro":{"draws":17,"losses":24,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":10,"wins":20},"o3":{"draws":25,"losses":23,"wins":16},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":39,"losses":3,"wins":24},"qwen/qwen3.7-max":{"draws":19,"losses":29,"wins":10},"qwen/qwen3.7-plus":{"draws":16,"losses":24,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":24,"wins":2},"qwen/qwen3.8-27b":{"draws":9,"losses":15,"wins":4},"qwen/qwen3.8-flash":{"draws":11,"losses":11,"wins":2},"qwen/qwen3.8-max":{"draws":5,"losses":16,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":12,"wins":1},"stealth/ox-alpha":{"draws":10,"losses":39,"wins":11},"stepfun/step-3.7-flash":{"draws":14,"losses":18,"wins":6},"tencent/hy3-preview":{"draws":10,"losses":19,"wins":7},"tencent/hy4-preview":{"draws":10,"losses":9,"wins":1},"thinkingmachines/inkling":{"draws":16,"losses":23,"wins":25},"thinkingmachines/inkling-small":{"draws":10,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":9,"losses":33,"wins":4},"x-ai/grok-4.6":{"draws":8,"losses":8,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":7,"wins":0},"x-ai/grok-build-0.1":{"draws":11,"losses":17,"wins":4},"xiaomi/mimo-v2.5":{"draws":46,"losses":39,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":23,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":11,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":21,"losses":45,"wins":14},"z-ai/glm-5.3":{"draws":0,"losses":8,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":18,"wins":0},"z-ai/glm-5.3-flashx":{"draws":1,"losses":8,"wins":1}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":49,"losses":33,"wins":60},"claude-fable-5":{"draws":29,"losses":90,"wins":13},"claude-fable-5-1":{"draws":6,"losses":115,"wins":1},"claude-opus-4-5":{"draws":63,"losses":86,"wins":45},"claude-opus-4-8":{"draws":35,"losses":49,"wins":4},"claude-opus-5":{"draws":19,"losses":107,"wins":10},"claude-opus-5-5":{"draws":0,"losses":25,"wins":1},"claude-sonnet-5":{"draws":64,"losses":78,"wins":36},"cohere/north-mini-code":{"draws":23,"losses":17,"wins":22},"deepseek/deepseek-v4-flash":{"draws":46,"losses":69,"wins":69},"deepseek/deepseek-v4-pro":{"draws":52,"losses":68,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":55,"losses":60,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":43,"wins":5},"google/gemini-3.1-flash-lite":{"draws":26,"losses":37,"wins":69},"google/gemini-3.5-flash":{"draws":53,"losses":62,"wins":37},"google/gemini-3.5-flash-lite":{"draws":106,"losses":93,"wins":107},"google/gemini-3.6-flash":{"draws":81,"losses":149,"wins":52},"google/gemini-3.8-flash":{"draws":32,"losses":88,"wins":20},"google/gemma-4-31b-it":{"draws":17,"losses":20,"wins":35},"gpt-4.1":{"draws":26,"losses":19,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":6,"wins":2},"gpt-5":{"draws":34,"losses":36,"wins":10},"gpt-5.4":{"draws":49,"losses":70,"wins":23},"gpt-5.4-mini":{"draws":41,"losses":27,"wins":18},"gpt-5.4-nano":{"draws":34,"losses":38,"wins":48},"gpt-5.5":{"draws":42,"losses":30,"wins":6},"gpt-5.6-luna":{"draws":75,"losses":46,"wins":49},"gpt-5.6-sol":{"draws":21,"losses":98,"wins":19},"gpt-5.6-terra":{"draws":62,"losses":67,"wins":35},"gpt-6-astra":{"draws":5,"losses":104,"wins":3},"gpt-6-luna":{"draws":6,"losses":10,"wins":6},"gpt-6-sol":{"draws":4,"losses":31,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":16,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":56,"losses":13,"wins":51},"inclusionai/ling-3.0-flash":{"draws":49,"losses":33,"wins":42},"meituan/longcat-2.0":{"draws":53,"losses":34,"wins":51},"meta/muse-glimmer-30b":{"draws":76,"losses":27,"wins":49},"meta/muse-spark-1.2":{"draws":22,"losses":45,"wins":19},"meta/muse-spark-1.3":{"draws":36,"losses":77,"wins":25},"minimax/minimax-m3":{"draws":32,"losses":30,"wins":30},"mistralai/mistral-medium-3-5":{"draws":41,"losses":16,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":14,"wins":10},"moonshotai/kimi-k3":{"draws":49,"losses":59,"wins":42},"nex-agi/nex-n2-pro":{"draws":18,"losses":26,"wins":32},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":52,"losses":27,"wins":37},"o3":{"draws":32,"losses":92,"wins":72},"openai/gpt-oss-120b":{"draws":63,"losses":40,"wins":45},"poolside/laguna-s-2.1":{"draws":70,"losses":35,"wins":43},"qwen/qwen3.7-max":{"draws":29,"losses":23,"wins":16},"qwen/qwen3.7-plus":{"draws":25,"losses":28,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":53,"losses":74,"wins":31},"qwen/qwen3.8-27b":{"draws":20,"losses":45,"wins":33},"qwen/qwen3.8-flash":{"draws":41,"losses":43,"wins":20},"qwen/qwen3.8-max":{"draws":61,"losses":65,"wins":28},"qwen/qwen3.8-max-0902":{"draws":6,"losses":30,"wins":4},"stealth/ox-alpha":{"draws":153,"losses":208,"wins":104},"stepfun/step-3.7-flash":{"draws":23,"losses":31,"wins":22},"tencent/hy3-preview":{"draws":24,"losses":27,"wins":21},"tencent/hy4-preview":{"draws":40,"losses":67,"wins":27},"thinkingmachines/inkling":{"draws":57,"losses":53,"wins":56},"thinkingmachines/inkling-small":{"draws":84,"losses":24,"wins":68},"x-ai/grok-4.5":{"draws":29,"losses":73,"wins":24},"x-ai/grok-4.6":{"draws":50,"losses":95,"wins":17},"x-ai/grok-4.7":{"draws":2,"losses":23,"wins":1},"x-ai/grok-build-0.1":{"draws":20,"losses":13,"wins":15},"xiaomi/mimo-v2.5":{"draws":95,"losses":83,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":26,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":12,"losses":19,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":2},"z-ai/glm-5.2":{"draws":101,"losses":104,"wins":61},"z-ai/glm-5.3":{"draws":36,"losses":75,"wins":7},"z-ai/glm-5.3-flash":{"draws":41,"losses":56,"wins":27},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":2}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":38,"losses":35,"wins":61},"claude-fable-5":{"draws":25,"losses":63,"wins":34},"claude-fable-5-1":{"draws":8,"losses":117,"wins":3},"claude-opus-4-5":{"draws":29,"losses":39,"wins":46},"claude-opus-4-8":{"draws":8,"losses":17,"wins":15},"claude-opus-5":{"draws":5,"losses":49,"wins":6},"claude-opus-5-5":{"draws":1,"losses":25,"wins":0},"claude-sonnet-5":{"draws":48,"losses":42,"wins":44},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":52,"losses":30,"wins":68},"deepseek/deepseek-v4-pro":{"draws":28,"losses":32,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":50,"losses":51,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":8,"wins":5},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":39,"losses":50,"wins":53},"google/gemini-3.5-flash-lite":{"draws":83,"losses":63,"wins":118},"google/gemini-3.6-flash":{"draws":58,"losses":81,"wins":79},"google/gemini-3.8-flash":{"draws":43,"losses":66,"wins":25},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":11},"gpt-4.1":{"draws":3,"losses":0,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":5,"wins":1},"gpt-5":{"draws":20,"losses":10,"wins":14},"gpt-5.4":{"draws":42,"losses":51,"wins":33},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":7},"gpt-5.4-nano":{"draws":11,"losses":3,"wins":22},"gpt-5.5":{"draws":7,"losses":23,"wins":8},"gpt-5.6-luna":{"draws":45,"losses":29,"wins":50},"gpt-5.6-sol":{"draws":15,"losses":67,"wins":36},"gpt-5.6-terra":{"draws":44,"losses":35,"wins":49},"gpt-6-astra":{"draws":4,"losses":88,"wins":12},"gpt-6-luna":{"draws":7,"losses":16,"wins":3},"gpt-6-sol":{"draws":1,"losses":11,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":45,"losses":12,"wins":37},"inclusionai/ling-3.0-flash":{"draws":15,"losses":6,"wins":27},"meituan/longcat-2.0":{"draws":25,"losses":11,"wins":48},"meta/muse-glimmer-30b":{"draws":45,"losses":24,"wins":47},"meta/muse-spark-1.2":{"draws":14,"losses":41,"wins":39},"meta/muse-spark-1.3":{"draws":22,"losses":51,"wins":39},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":7},"mistralai/mistral-medium-3-5":{"draws":27,"losses":9,"wins":40},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":41,"losses":38,"wins":31},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":12},"o3":{"draws":27,"losses":46,"wins":77},"openai/gpt-oss-120b":{"draws":44,"losses":26,"wins":44},"poolside/laguna-s-2.1":{"draws":34,"losses":24,"wins":36},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-plus":{"draws":12,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":56,"wins":37},"qwen/qwen3.8-27b":{"draws":15,"losses":35,"wins":26},"qwen/qwen3.8-flash":{"draws":27,"losses":31,"wins":30},"qwen/qwen3.8-max":{"draws":36,"losses":53,"wins":37},"qwen/qwen3.8-max-0902":{"draws":2,"losses":8,"wins":2},"stealth/ox-alpha":{"draws":133,"losses":156,"wins":139},"stepfun/step-3.7-flash":{"draws":12,"losses":2,"wins":26},"tencent/hy3-preview":{"draws":13,"losses":4,"wins":5},"tencent/hy4-preview":{"draws":40,"losses":58,"wins":40},"thinkingmachines/inkling":{"draws":35,"losses":13,"wins":46},"thinkingmachines/inkling-small":{"draws":62,"losses":21,"wins":65},"x-ai/grok-4.5":{"draws":26,"losses":34,"wins":38},"x-ai/grok-4.6":{"draws":38,"losses":61,"wins":33},"x-ai/grok-4.7":{"draws":2,"losses":14,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":20,"losses":6,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":11,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":58,"losses":59,"wins":65},"z-ai/glm-5.3":{"draws":24,"losses":76,"wins":22},"z-ai/glm-5.3-flash":{"draws":40,"losses":54,"wins":36},"z-ai/glm-5.3-flashx":{"draws":5,"losses":6,"wins":5}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":38,"losses":34,"wins":50},"claude-fable-5":{"draws":27,"losses":71,"wins":20},"claude-fable-5-1":{"draws":6,"losses":124,"wins":4},"claude-opus-4-5":{"draws":29,"losses":42,"wins":49},"claude-opus-4-8":{"draws":8,"losses":16,"wins":16},"claude-opus-5":{"draws":7,"losses":44,"wins":9},"claude-opus-5-5":{"draws":0,"losses":24,"wins":0},"claude-sonnet-5":{"draws":42,"losses":31,"wins":53},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":18},"deepseek/deepseek-v4-flash":{"draws":55,"losses":35,"wins":60},"deepseek/deepseek-v4-pro":{"draws":50,"losses":41,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":25,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":10,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":5,"wins":10},"google/gemini-3.5-flash":{"draws":51,"losses":65,"wins":42},"google/gemini-3.5-flash-lite":{"draws":87,"losses":48,"wins":93},"google/gemini-3.6-flash":{"draws":71,"losses":103,"wins":66},"google/gemini-3.8-flash":{"draws":40,"losses":61,"wins":41},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":5,"wins":1},"gpt-5":{"draws":20,"losses":11,"wins":21},"gpt-5.4":{"draws":44,"losses":45,"wins":31},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":10,"wins":18},"gpt-5.5":{"draws":7,"losses":8,"wins":7},"gpt-5.6-luna":{"draws":41,"losses":38,"wins":41},"gpt-5.6-sol":{"draws":22,"losses":75,"wins":29},"gpt-5.6-terra":{"draws":41,"losses":44,"wins":45},"gpt-6-astra":{"draws":7,"losses":106,"wins":1},"gpt-6-luna":{"draws":4,"losses":6,"wins":8},"gpt-6-sol":{"draws":3,"losses":15,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":12,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":38,"losses":13,"wins":43},"inclusionai/ling-3.0-flash":{"draws":19,"losses":9,"wins":12},"meituan/longcat-2.0":{"draws":36,"losses":15,"wins":39},"meta/muse-glimmer-30b":{"draws":54,"losses":21,"wins":55},"meta/muse-spark-1.2":{"draws":31,"losses":37,"wins":32},"meta/muse-spark-1.3":{"draws":30,"losses":58,"wins":30},"minimax/minimax-m3":{"draws":6,"losses":4,"wins":14},"mistralai/mistral-medium-3-5":{"draws":24,"losses":13,"wins":41},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":37,"losses":32,"wins":35},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":4,"wins":17},"o3":{"draws":29,"losses":39,"wins":66},"openai/gpt-oss-120b":{"draws":38,"losses":22,"wins":30},"poolside/laguna-s-2.1":{"draws":42,"losses":18,"wins":34},"qwen/qwen3.7-max":{"draws":3,"losses":6,"wins":13},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":40,"losses":44,"wins":48},"qwen/qwen3.8-27b":{"draws":28,"losses":36,"wins":28},"qwen/qwen3.8-flash":{"draws":39,"losses":26,"wins":25},"qwen/qwen3.8-max":{"draws":46,"losses":41,"wins":39},"qwen/qwen3.8-max-0902":{"draws":9,"losses":2,"wins":5},"stealth/ox-alpha":{"draws":131,"losses":169,"wins":142},"stepfun/step-3.7-flash":{"draws":14,"losses":8,"wins":16},"tencent/hy3-preview":{"draws":14,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":32,"losses":50,"wins":38},"thinkingmachines/inkling":{"draws":35,"losses":26,"wins":39},"thinkingmachines/inkling-small":{"draws":51,"losses":24,"wins":65},"x-ai/grok-4.5":{"draws":27,"losses":34,"wins":35},"x-ai/grok-4.6":{"draws":53,"losses":55,"wins":36},"x-ai/grok-4.7":{"draws":0,"losses":12,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":27,"losses":10,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":13,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":60,"losses":52,"wins":72},"z-ai/glm-5.3":{"draws":26,"losses":65,"wins":25},"z-ai/glm-5.3-flash":{"draws":39,"losses":57,"wins":38},"z-ai/glm-5.3-flashx":{"draws":2,"losses":13,"wins":1}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":6,"wins":10},"claude-fable-5":{"draws":10,"losses":10,"wins":8},"claude-fable-5-1":{"draws":6,"losses":37,"wins":5},"claude-opus-4-5":{"draws":7,"losses":5,"wins":28},"claude-opus-4-8":{"draws":3,"losses":9,"wins":8},"claude-opus-5":{"draws":10,"losses":19,"wins":9},"claude-opus-5-5":{"draws":0,"losses":39,"wins":3},"claude-sonnet-5":{"draws":12,"losses":5,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":18},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":43},"deepseek/deepseek-v4-pro":{"draws":5,"losses":5,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":2,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":24,"losses":36,"wins":36},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":20},"google/gemini-3.5-flash":{"draws":3,"losses":6,"wins":11},"google/gemini-3.5-flash-lite":{"draws":10,"losses":16,"wins":30},"google/gemini-3.6-flash":{"draws":19,"losses":24,"wins":23},"google/gemini-3.8-flash":{"draws":3,"losses":7,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":9},"gpt-4.1":{"draws":5,"losses":5,"wins":12},"gpt-5":{"draws":8,"losses":7,"wins":7},"gpt-5.4":{"draws":14,"losses":22,"wins":8},"gpt-5.4-mini":{"draws":9,"losses":7,"wins":10},"gpt-5.4-nano":{"draws":10,"losses":4,"wins":12},"gpt-5.5":{"draws":12,"losses":6,"wins":8},"gpt-5.6-luna":{"draws":14,"losses":3,"wins":17},"gpt-5.6-sol":{"draws":2,"losses":9,"wins":7},"gpt-5.6-terra":{"draws":5,"losses":2,"wins":9},"gpt-6-astra":{"draws":4,"losses":26,"wins":2},"gpt-6-luna":{"draws":20,"losses":10,"wins":16},"gpt-6-sol":{"draws":13,"losses":23,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":3},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":18},"meituan/longcat-2.0":{"draws":18,"losses":10,"wins":26},"meta/muse-glimmer-30b":{"draws":17,"losses":3,"wins":18},"meta/muse-spark-1.2":{"draws":9,"losses":6,"wins":9},"meta/muse-spark-1.3":{"draws":18,"losses":6,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":7},"moonshotai/kimi-k3":{"draws":8,"losses":6,"wins":12},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":6,"wins":6},"o3":{"draws":7,"losses":9,"wins":20},"openai/gpt-oss-120b":{"draws":11,"losses":8,"wins":19},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":2},"qwen/qwen3.7-max":{"draws":7,"losses":7,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":16,"wins":15},"qwen/qwen3.8-27b":{"draws":3,"losses":5,"wins":4},"qwen/qwen3.8-flash":{"draws":6,"losses":8,"wins":8},"qwen/qwen3.8-max":{"draws":13,"losses":10,"wins":15},"qwen/qwen3.8-max-0902":{"draws":17,"losses":20,"wins":21},"stealth/ox-alpha":{"draws":23,"losses":48,"wins":35},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":11},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":7},"tencent/hy4-preview":{"draws":8,"losses":10,"wins":12},"thinkingmachines/inkling":{"draws":13,"losses":1,"wins":10},"thinkingmachines/inkling-small":{"draws":8,"losses":3,"wins":15},"x-ai/grok-4.5":{"draws":5,"losses":10,"wins":1},"x-ai/grok-4.6":{"draws":13,"losses":15,"wins":6},"x-ai/grok-4.7":{"draws":5,"losses":8,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":21,"losses":3,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":4},"z-ai/glm-5.2":{"draws":15,"losses":14,"wins":21},"z-ai/glm-5.3":{"draws":10,"losses":14,"wins":8},"z-ai/glm-5.3-flash":{"draws":3,"losses":8,"wins":11},"z-ai/glm-5.3-flashx":{"draws":17,"losses":21,"wins":10}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":18,"wins":7},"claude-fable-5":{"draws":2,"losses":10,"wins":2},"claude-fable-5-1":{"draws":2,"losses":28,"wins":0},"claude-opus-4-5":{"draws":35,"losses":89,"wins":8},"claude-opus-4-8":{"draws":25,"losses":68,"wins":5},"claude-opus-5":{"draws":19,"losses":69,"wins":4},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":14,"losses":27,"wins":3},"cohere/north-mini-code":{"draws":15,"losses":32,"wins":27},"deepseek/deepseek-v4-flash":{"draws":26,"losses":69,"wins":37},"deepseek/deepseek-v4-pro":{"draws":9,"losses":10,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":10,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":20,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":32,"wins":32},"google/gemini-3.5-flash":{"draws":11,"losses":23,"wins":8},"google/gemini-3.5-flash-lite":{"draws":30,"losses":43,"wins":21},"google/gemini-3.6-flash":{"draws":11,"losses":49,"wins":4},"google/gemini-3.8-flash":{"draws":5,"losses":19,"wins":2},"google/gemma-4-31b-it":{"draws":22,"losses":33,"wins":27},"gpt-4.1":{"draws":14,"losses":18,"wins":6},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":32,"losses":40,"wins":2},"gpt-5.4":{"draws":5,"losses":25,"wins":2},"gpt-5.4-mini":{"draws":19,"losses":34,"wins":11},"gpt-5.4-nano":{"draws":18,"losses":78,"wins":30},"gpt-5.5":{"draws":23,"losses":34,"wins":5},"gpt-5.6-luna":{"draws":7,"losses":7,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":16,"wins":2},"gpt-5.6-terra":{"draws":9,"losses":35,"wins":6},"gpt-6-astra":{"draws":0,"losses":24,"wins":0},"gpt-6-luna":{"draws":5,"losses":14,"wins":5},"gpt-6-sol":{"draws":4,"losses":26,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":6,"wins":2},"inclusionai/ling-3.0-flash":{"draws":19,"losses":19,"wins":26},"meituan/longcat-2.0":{"draws":15,"losses":43,"wins":26},"meta/muse-glimmer-30b":{"draws":16,"losses":9,"wins":5},"meta/muse-spark-1.2":{"draws":9,"losses":12,"wins":1},"meta/muse-spark-1.3":{"draws":6,"losses":16,"wins":0},"minimax/minimax-m3":{"draws":20,"losses":32,"wins":30},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":23,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":17,"wins":2},"nex-agi/nex-n2-pro":{"draws":14,"losses":28,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":42,"wins":29},"o3":{"draws":12,"losses":61,"wins":5},"openai/gpt-oss-120b":{"draws":6,"losses":19,"wins":5},"poolside/laguna-s-2.1":{"draws":14,"losses":31,"wins":19},"qwen/qwen3.7-max":{"draws":20,"losses":33,"wins":13},"qwen/qwen3.7-plus":{"draws":19,"losses":31,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":14,"wins":0},"qwen/qwen3.8-27b":{"draws":7,"losses":19,"wins":4},"qwen/qwen3.8-flash":{"draws":14,"losses":6,"wins":2},"qwen/qwen3.8-max":{"draws":5,"losses":9,"wins":0},"qwen/qwen3.8-max-0902":{"draws":5,"losses":25,"wins":0},"stealth/ox-alpha":{"draws":17,"losses":38,"wins":9},"stepfun/step-3.7-flash":{"draws":12,"losses":37,"wins":7},"tencent/hy3-preview":{"draws":20,"losses":18,"wins":16},"tencent/hy4-preview":{"draws":6,"losses":18,"wins":0},"thinkingmachines/inkling":{"draws":30,"losses":47,"wins":29},"thinkingmachines/inkling-small":{"draws":8,"losses":11,"wins":3},"x-ai/grok-4.5":{"draws":13,"losses":40,"wins":1},"x-ai/grok-4.6":{"draws":1,"losses":12,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":11,"wins":1},"x-ai/grok-build-0.1":{"draws":11,"losses":22,"wins":7},"xiaomi/mimo-v2.5":{"draws":66,"losses":77,"wins":45},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":47,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":10,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":9,"wins":0},"z-ai/glm-5.2":{"draws":40,"losses":73,"wins":19},"z-ai/glm-5.3":{"draws":5,"losses":18,"wins":1},"z-ai/glm-5.3-flash":{"draws":1,"losses":15,"wins":4},"z-ai/glm-5.3-flashx":{"draws":3,"losses":27,"wins":0}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":41,"losses":29,"wins":56},"claude-fable-5":{"draws":31,"losses":93,"wins":30},"claude-fable-5-1":{"draws":14,"losses":138,"wins":10},"claude-opus-4-5":{"draws":39,"losses":55,"wins":78},"claude-opus-4-8":{"draws":34,"losses":34,"wins":12},"claude-opus-5":{"draws":16,"losses":98,"wins":14},"claude-opus-5-5":{"draws":1,"losses":32,"wins":3},"claude-sonnet-5":{"draws":51,"losses":46,"wins":61},"cohere/north-mini-code":{"draws":12,"losses":7,"wins":17},"deepseek/deepseek-v4-flash":{"draws":53,"losses":37,"wins":62},"deepseek/deepseek-v4-pro":{"draws":39,"losses":53,"wins":50},"deepseek/deepseek-v4-pro-0813":{"draws":51,"losses":42,"wins":65},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":11,"losses":8,"wins":23},"google/gemini-3.5-flash":{"draws":24,"losses":36,"wins":36},"google/gemini-3.5-flash-lite":{"draws":85,"losses":75,"wins":122},"google/gemini-3.6-flash":{"draws":62,"losses":82,"wins":92},"google/gemini-3.8-flash":{"draws":36,"losses":75,"wins":45},"google/gemma-4-31b-it":{"draws":12,"losses":2,"wins":12},"gpt-4.1":{"draws":5,"losses":4,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":16,"losses":20,"wins":26},"gpt-5.4":{"draws":29,"losses":59,"wins":50},"gpt-5.4-mini":{"draws":14,"losses":9,"wins":21},"gpt-5.4-nano":{"draws":19,"losses":18,"wins":45},"gpt-5.5":{"draws":20,"losses":20,"wins":12},"gpt-5.6-luna":{"draws":55,"losses":32,"wins":51},"gpt-5.6-sol":{"draws":21,"losses":91,"wins":44},"gpt-5.6-terra":{"draws":49,"losses":52,"wins":43},"gpt-6-astra":{"draws":18,"losses":124,"wins":6},"gpt-6-luna":{"draws":8,"losses":12,"wins":20},"gpt-6-sol":{"draws":7,"losses":22,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":11},"inception/mercury-2.5-preview":{"draws":38,"losses":7,"wins":41},"inclusionai/ling-3.0-flash":{"draws":25,"losses":5,"wins":34},"meituan/longcat-2.0":{"draws":26,"losses":22,"wins":74},"meta/muse-glimmer-30b":{"draws":36,"losses":27,"wins":51},"meta/muse-spark-1.2":{"draws":25,"losses":36,"wins":51},"meta/muse-spark-1.3":{"draws":23,"losses":73,"wins":40},"minimax/minimax-m3":{"draws":16,"losses":10,"wins":14},"mistralai/mistral-medium-3-5":{"draws":23,"losses":14,"wins":39},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":61,"losses":30,"wins":53},"nex-agi/nex-n2-pro":{"draws":9,"losses":10,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":8,"wins":12},"o3":{"draws":24,"losses":53,"wins":93},"openai/gpt-oss-120b":{"draws":43,"losses":25,"wins":54},"poolside/laguna-s-2.1":{"draws":42,"losses":22,"wins":48},"qwen/qwen3.7-max":{"draws":19,"losses":16,"wins":13},"qwen/qwen3.7-plus":{"draws":13,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":58,"wins":51},"qwen/qwen3.8-27b":{"draws":21,"losses":41,"wins":24},"qwen/qwen3.8-flash":{"draws":41,"losses":23,"wins":42},"qwen/qwen3.8-max":{"draws":49,"losses":34,"wins":53},"qwen/qwen3.8-max-0902":{"draws":8,"losses":7,"wins":7},"stealth/ox-alpha":{"draws":118,"losses":194,"wins":179},"stepfun/step-3.7-flash":{"draws":13,"losses":13,"wins":28},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":33,"losses":77,"wins":48},"thinkingmachines/inkling":{"draws":37,"losses":32,"wins":49},"thinkingmachines/inkling-small":{"draws":39,"losses":27,"wins":62},"x-ai/grok-4.5":{"draws":29,"losses":50,"wins":37},"x-ai/grok-4.6":{"draws":39,"losses":70,"wins":33},"x-ai/grok-4.7":{"draws":0,"losses":18,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":26,"losses":17,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":19,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":9,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":66,"losses":76,"wins":72},"z-ai/glm-5.3":{"draws":26,"losses":83,"wins":33},"z-ai/glm-5.3-flash":{"draws":46,"losses":52,"wins":54},"z-ai/glm-5.3-flashx":{"draws":11,"losses":9,"wins":8}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":90,"losses":87,"wins":79},"claude-fable-5":{"draws":44,"losses":137,"wins":31},"claude-fable-5-1":{"draws":16,"losses":169,"wins":1},"claude-opus-4-5":{"draws":177,"losses":238,"wins":117},"claude-opus-4-8":{"draws":36,"losses":56,"wins":16},"claude-opus-5":{"draws":31,"losses":201,"wins":20},"claude-opus-5-5":{"draws":5,"losses":33,"wins":0},"claude-sonnet-5":{"draws":145,"losses":261,"wins":118},"cohere/north-mini-code":{"draws":35,"losses":13,"wins":14},"deepseek/deepseek-v4-flash":{"draws":106,"losses":107,"wins":93},"deepseek/deepseek-v4-pro":{"draws":83,"losses":118,"wins":63},"deepseek/deepseek-v4-pro-0813":{"draws":87,"losses":93,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":30,"wins":16},"google/gemini-3.1-flash-lite":{"draws":30,"losses":21,"wins":43},"google/gemini-3.5-flash":{"draws":85,"losses":122,"wins":75},"google/gemini-3.5-flash-lite":{"draws":332,"losses":346,"wins":346},"google/gemini-3.6-flash":{"draws":341,"losses":477,"wins":209},"google/gemini-3.8-flash":{"draws":46,"losses":139,"wins":11},"google/gemma-4-31b-it":{"draws":19,"losses":24,"wins":21},"gpt-4.1":{"draws":15,"losses":12,"wins":17},"gpt-4.1-nano":{"draws":3,"losses":17,"wins":14},"gpt-5":{"draws":41,"losses":29,"wins":22},"gpt-5.4":{"draws":133,"losses":260,"wins":65},"gpt-5.4-mini":{"draws":30,"losses":38,"wins":26},"gpt-5.4-nano":{"draws":33,"losses":33,"wins":54},"gpt-5.5":{"draws":49,"losses":30,"wins":11},"gpt-5.6-luna":{"draws":174,"losses":200,"wins":160},"gpt-5.6-sol":{"draws":70,"losses":355,"wins":41},"gpt-5.6-terra":{"draws":74,"losses":110,"wins":52},"gpt-6-astra":{"draws":13,"losses":154,"wins":1},"gpt-6-luna":{"draws":10,"losses":31,"wins":11},"gpt-6-sol":{"draws":9,"losses":53,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":25,"losses":0,"wins":9},"inception/mercury-2.5-preview":{"draws":96,"losses":36,"wins":80},"inclusionai/ling-3.0-flash":{"draws":92,"losses":47,"wins":127},"meituan/longcat-2.0":{"draws":111,"losses":155,"wins":178},"meta/muse-glimmer-30b":{"draws":100,"losses":56,"wins":84},"meta/muse-spark-1.2":{"draws":89,"losses":177,"wins":72},"meta/muse-spark-1.3":{"draws":42,"losses":113,"wins":45},"minimax/minimax-m3":{"draws":21,"losses":22,"wins":25},"mistralai/mistral-medium-3-5":{"draws":60,"losses":34,"wins":68},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":5,"wins":11},"moonshotai/kimi-k3":{"draws":190,"losses":260,"wins":108},"nex-agi/nex-n2-pro":{"draws":26,"losses":8,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":27,"wins":33},"o3":{"draws":111,"losses":383,"wins":230},"openai/gpt-oss-120b":{"draws":91,"losses":75,"wins":84},"poolside/laguna-s-2.1":{"draws":192,"losses":141,"wins":119},"qwen/qwen3.7-max":{"draws":25,"losses":14,"wins":27},"qwen/qwen3.7-plus":{"draws":25,"losses":12,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":79,"losses":112,"wins":41},"qwen/qwen3.8-27b":{"draws":29,"losses":78,"wins":33},"qwen/qwen3.8-flash":{"draws":62,"losses":66,"wins":30},"qwen/qwen3.8-max":{"draws":83,"losses":87,"wins":55},"qwen/qwen3.8-max-0902":{"draws":12,"losses":21,"wins":5},"stealth/ox-alpha":{"draws":204,"losses":387,"wins":168},"stepfun/step-3.7-flash":{"draws":44,"losses":70,"wins":58},"tencent/hy3-preview":{"draws":33,"losses":22,"wins":9},"tencent/hy4-preview":{"draws":80,"losses":110,"wins":46},"thinkingmachines/inkling":{"draws":183,"losses":127,"wins":196},"thinkingmachines/inkling-small":{"draws":107,"losses":94,"wins":103},"x-ai/grok-4.5":{"draws":125,"losses":257,"wins":96},"x-ai/grok-4.6":{"draws":71,"losses":122,"wins":33},"x-ai/grok-4.7":{"draws":3,"losses":21,"wins":8},"x-ai/grok-build-0.1":{"draws":21,"losses":15,"wins":14},"xiaomi/mimo-v2.5":{"draws":57,"losses":42,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":31,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":10,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":137,"losses":112,"wins":105},"z-ai/glm-5.3":{"draws":44,"losses":155,"wins":17},"z-ai/glm-5.3-flash":{"draws":65,"losses":117,"wins":42},"z-ai/glm-5.3-flashx":{"draws":7,"losses":30,"wins":5}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":60,"losses":51,"wins":89},"claude-fable-5":{"draws":39,"losses":105,"wins":66},"claude-fable-5-1":{"draws":12,"losses":193,"wins":23},"claude-opus-4-5":{"draws":128,"losses":164,"wins":204},"claude-opus-4-8":{"draws":34,"losses":49,"wins":59},"claude-opus-5":{"draws":39,"losses":189,"wins":50},"claude-opus-5-5":{"draws":4,"losses":40,"wins":2},"claude-sonnet-5":{"draws":112,"losses":147,"wins":189},"cohere/north-mini-code":{"draws":27,"losses":12,"wins":51},"deepseek/deepseek-v4-flash":{"draws":81,"losses":52,"wins":149},"deepseek/deepseek-v4-pro":{"draws":58,"losses":79,"wins":81},"deepseek/deepseek-v4-pro-0813":{"draws":71,"losses":66,"wins":103},"deepseek/deepseek-v4.1-flash":{"draws":19,"losses":23,"wins":24},"google/gemini-3.1-flash-lite":{"draws":11,"losses":4,"wins":49},"google/gemini-3.5-flash":{"draws":62,"losses":92,"wins":82},"google/gemini-3.5-flash-lite":{"draws":341,"losses":209,"wins":477},"google/gemini-3.6-flash":{"draws":172,"losses":304,"wins":304},"google/gemini-3.8-flash":{"draws":45,"losses":100,"wins":80},"google/gemma-4-31b-it":{"draws":14,"losses":13,"wins":21},"gpt-4.1":{"draws":19,"losses":11,"wins":26},"gpt-4.1-nano":{"draws":16,"losses":10,"wins":4},"gpt-5":{"draws":25,"losses":41,"wins":48},"gpt-5.4":{"draws":111,"losses":196,"wins":133},"gpt-5.4-mini":{"draws":30,"losses":19,"wins":48},"gpt-5.4-nano":{"draws":37,"losses":30,"wins":47},"gpt-5.5":{"draws":47,"losses":44,"wins":49},"gpt-5.6-luna":{"draws":134,"losses":108,"wins":214},"gpt-5.6-sol":{"draws":61,"losses":245,"wins":134},"gpt-5.6-terra":{"draws":66,"losses":60,"wins":88},"gpt-6-astra":{"draws":21,"losses":168,"wins":15},"gpt-6-luna":{"draws":16,"losses":10,"wins":30},"gpt-6-sol":{"draws":7,"losses":38,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":7,"losses":0,"wins":19},"inception/mercury-2.5-preview":{"draws":64,"losses":14,"wins":82},"inclusionai/ling-3.0-flash":{"draws":118,"losses":39,"wins":109},"meituan/longcat-2.0":{"draws":115,"losses":71,"wins":203},"meta/muse-glimmer-30b":{"draws":92,"losses":31,"wins":95},"meta/muse-spark-1.2":{"draws":64,"losses":154,"wins":130},"meta/muse-spark-1.3":{"draws":36,"losses":93,"wins":71},"minimax/minimax-m3":{"draws":17,"losses":10,"wins":39},"mistralai/mistral-medium-3-5":{"draws":44,"losses":18,"wins":56},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":4,"wins":20},"moonshotai/kimi-k3":{"draws":156,"losses":177,"wins":215},"nex-agi/nex-n2-pro":{"draws":18,"losses":13,"wins":41},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":9,"wins":54},"o3":{"draws":112,"losses":221,"wins":329},"openai/gpt-oss-120b":{"draws":72,"losses":29,"wins":81},"poolside/laguna-s-2.1":{"draws":167,"losses":61,"wins":158},"qwen/qwen3.7-max":{"draws":16,"losses":14,"wins":42},"qwen/qwen3.7-plus":{"draws":23,"losses":12,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":66,"losses":78,"wins":102},"qwen/qwen3.8-27b":{"draws":35,"losses":38,"wins":67},"qwen/qwen3.8-flash":{"draws":66,"losses":39,"wins":59},"qwen/qwen3.8-max":{"draws":70,"losses":88,"wins":95},"qwen/qwen3.8-max-0902":{"draws":15,"losses":11,"wins":18},"stealth/ox-alpha":{"draws":177,"losses":287,"wins":297},"stepfun/step-3.7-flash":{"draws":27,"losses":21,"wins":103},"tencent/hy3-preview":{"draws":25,"losses":21,"wins":32},"tencent/hy4-preview":{"draws":56,"losses":97,"wins":105},"thinkingmachines/inkling":{"draws":168,"losses":72,"wins":238},"thinkingmachines/inkling-small":{"draws":76,"losses":50,"wins":102},"x-ai/grok-4.5":{"draws":100,"losses":190,"wins":208},"x-ai/grok-4.6":{"draws":61,"losses":88,"wins":69},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":6},"x-ai/grok-build-0.1":{"draws":17,"losses":0,"wins":19},"xiaomi/mimo-v2.5":{"draws":68,"losses":30,"wins":82},"xiaomi/mimo-v2.5-pro":{"draws":24,"losses":23,"wins":37},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":15,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":9,"wins":10},"z-ai/glm-5.2":{"draws":93,"losses":87,"wins":122},"z-ai/glm-5.3":{"draws":33,"losses":140,"wins":43},"z-ai/glm-5.3-flash":{"draws":54,"losses":98,"wins":70},"z-ai/glm-5.3-flashx":{"draws":16,"losses":13,"wins":19}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":21,"wins":56},"claude-fable-5":{"draws":25,"losses":70,"wins":51},"claude-fable-5-1":{"draws":15,"losses":148,"wins":15},"claude-opus-4-5":{"draws":44,"losses":31,"wins":69},"claude-opus-4-8":{"draws":6,"losses":17,"wins":15},"claude-opus-5":{"draws":17,"losses":71,"wins":28},"claude-opus-5-5":{"draws":4,"losses":21,"wins":3},"claude-sonnet-5":{"draws":38,"losses":37,"wins":71},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":32,"losses":20,"wins":88},"deepseek/deepseek-v4-pro":{"draws":43,"losses":25,"wins":66},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":41,"wins":61},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":8,"wins":7},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":19},"google/gemini-3.5-flash":{"draws":36,"losses":45,"wins":75},"google/gemini-3.5-flash-lite":{"draws":46,"losses":11,"wins":139},"google/gemini-3.6-flash":{"draws":45,"losses":80,"wins":100},"google/gemini-3.8-flash":{"draws":28,"losses":38,"wins":38},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":11},"gpt-4.1":{"draws":5,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":13,"losses":14,"wins":25},"gpt-5.4":{"draws":40,"losses":61,"wins":57},"gpt-5.4-mini":{"draws":6,"losses":9,"wins":15},"gpt-5.4-nano":{"draws":7,"losses":6,"wins":27},"gpt-5.5":{"draws":8,"losses":16,"wins":10},"gpt-5.6-luna":{"draws":33,"losses":32,"wins":67},"gpt-5.6-sol":{"draws":20,"losses":79,"wins":61},"gpt-5.6-terra":{"draws":47,"losses":35,"wins":54},"gpt-6-astra":{"draws":19,"losses":134,"wins":11},"gpt-6-luna":{"draws":6,"losses":4,"wins":10},"gpt-6-sol":{"draws":2,"losses":12,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":13},"inception/mercury-2.5-preview":{"draws":37,"losses":3,"wins":40},"inclusionai/ling-3.0-flash":{"draws":13,"losses":2,"wins":33},"meituan/longcat-2.0":{"draws":20,"losses":10,"wins":39},"meta/muse-glimmer-30b":{"draws":36,"losses":15,"wins":47},"meta/muse-spark-1.2":{"draws":19,"losses":43,"wins":40},"meta/muse-spark-1.3":{"draws":20,"losses":57,"wins":45},"minimax/minimax-m3":{"draws":8,"losses":1,"wins":17},"mistralai/mistral-medium-3-5":{"draws":21,"losses":5,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":50,"losses":32,"wins":60},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":4,"wins":15},"o3":{"draws":18,"losses":40,"wins":90},"openai/gpt-oss-120b":{"draws":27,"losses":8,"wins":57},"poolside/laguna-s-2.1":{"draws":26,"losses":8,"wins":52},"qwen/qwen3.7-max":{"draws":4,"losses":11,"wins":15},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":52,"wins":67},"qwen/qwen3.8-27b":{"draws":19,"losses":30,"wins":51},"qwen/qwen3.8-flash":{"draws":25,"losses":21,"wins":48},"qwen/qwen3.8-max":{"draws":40,"losses":44,"wins":56},"qwen/qwen3.8-max-0902":{"draws":6,"losses":3,"wins":7},"stealth/ox-alpha":{"draws":115,"losses":157,"wins":216},"stepfun/step-3.7-flash":{"draws":11,"losses":1,"wins":24},"tencent/hy3-preview":{"draws":14,"losses":3,"wins":15},"tencent/hy4-preview":{"draws":26,"losses":49,"wins":43},"thinkingmachines/inkling":{"draws":31,"losses":8,"wins":49},"thinkingmachines/inkling-small":{"draws":49,"losses":16,"wins":55},"x-ai/grok-4.5":{"draws":23,"losses":61,"wins":36},"x-ai/grok-4.6":{"draws":44,"losses":55,"wins":53},"x-ai/grok-4.7":{"draws":3,"losses":16,"wins":7},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":26,"losses":6,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":8,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":8,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":46,"losses":40,"wins":90},"z-ai/glm-5.3":{"draws":23,"losses":88,"wins":39},"z-ai/glm-5.3-flash":{"draws":39,"losses":50,"wins":67},"z-ai/glm-5.3-flashx":{"draws":0,"losses":12,"wins":6}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":2},"claude-fable-5":{"draws":0,"losses":11,"wins":1},"claude-fable-5-1":{"draws":4,"losses":16,"wins":0},"claude-opus-4-5":{"draws":21,"losses":38,"wins":27},"claude-opus-4-8":{"draws":29,"losses":38,"wins":5},"claude-opus-5":{"draws":14,"losses":59,"wins":11},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":8,"losses":13,"wins":3},"cohere/north-mini-code":{"draws":11,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":17,"losses":35,"wins":20},"deepseek/deepseek-v4-pro":{"draws":1,"losses":11,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":4,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":9,"wins":1},"google/gemini-3.1-flash-lite":{"draws":22,"losses":27,"wins":33},"google/gemini-3.5-flash":{"draws":12,"losses":12,"wins":2},"google/gemini-3.5-flash-lite":{"draws":19,"losses":21,"wins":24},"google/gemini-3.6-flash":{"draws":14,"losses":21,"wins":13},"google/gemini-3.8-flash":{"draws":5,"losses":11,"wins":0},"google/gemma-4-31b-it":{"draws":12,"losses":10,"wins":10},"gpt-4.1":{"draws":9,"losses":11,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":21,"wins":6},"gpt-5.4":{"draws":3,"losses":12,"wins":3},"gpt-5.4-mini":{"draws":7,"losses":19,"wins":18},"gpt-5.4-nano":{"draws":8,"losses":38,"wins":32},"gpt-5.5":{"draws":24,"losses":22,"wins":4},"gpt-5.6-luna":{"draws":8,"losses":8,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":16,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":14,"wins":1},"gpt-6-astra":{"draws":0,"losses":14,"wins":0},"gpt-6-luna":{"draws":2,"losses":5,"wins":1},"gpt-6-sol":{"draws":1,"losses":4,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":7,"wins":12},"inclusionai/ling-3.0-flash":{"draws":16,"losses":13,"wins":25},"meituan/longcat-2.0":{"draws":15,"losses":31,"wins":28},"meta/muse-glimmer-30b":{"draws":2,"losses":6,"wins":6},"meta/muse-spark-1.2":{"draws":11,"losses":14,"wins":1},"meta/muse-spark-1.3":{"draws":2,"losses":15,"wins":5},"minimax/minimax-m3":{"draws":12,"losses":20,"wins":14},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":22,"wins":2},"moonshotai/kimi-k3":{"draws":9,"losses":33,"wins":6},"nex-agi/nex-n2-pro":{"draws":8,"losses":17,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":8,"wins":23},"o3":{"draws":12,"losses":31,"wins":9},"openai/gpt-oss-120b":{"draws":6,"losses":6,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":25,"wins":23},"qwen/qwen3.7-max":{"draws":6,"losses":31,"wins":13},"qwen/qwen3.7-plus":{"draws":4,"losses":14,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":17,"wins":0},"qwen/qwen3.8-27b":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":5},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":2},"qwen/qwen3.8-max-0902":{"draws":4,"losses":10,"wins":0},"stealth/ox-alpha":{"draws":11,"losses":40,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":26,"wins":4},"tencent/hy3-preview":{"draws":18,"losses":19,"wins":7},"tencent/hy4-preview":{"draws":4,"losses":11,"wins":1},"thinkingmachines/inkling":{"draws":12,"losses":21,"wins":15},"thinkingmachines/inkling-small":{"draws":3,"losses":7,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":20,"wins":4},"x-ai/grok-4.6":{"draws":4,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":11,"losses":18,"wins":9},"xiaomi/mimo-v2.5":{"draws":35,"losses":52,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":19,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":30,"losses":24,"wins":12},"z-ai/glm-5.3":{"draws":1,"losses":13,"wins":2},"z-ai/glm-5.3-flash":{"draws":2,"losses":18,"wins":2},"z-ai/glm-5.3-flashx":{"draws":2,"losses":6,"wins":0}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":2},"claude-fable-5":{"draws":0,"losses":4,"wins":4},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":35,"losses":12,"wins":11},"claude-opus-4-8":{"draws":19,"losses":24,"wins":7},"claude-opus-5":{"draws":12,"losses":70,"wins":7},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":2},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":26,"losses":7,"wins":19},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":8,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":12,"wins":5},"google/gemini-3.1-flash-lite":{"draws":14,"losses":6,"wins":18},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":4},"google/gemini-3.5-flash-lite":{"draws":15,"losses":17,"wins":12},"google/gemini-3.6-flash":{"draws":19,"losses":26,"wins":11},"google/gemini-3.8-flash":{"draws":5,"losses":6,"wins":3},"google/gemma-4-31b-it":{"draws":9,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":9,"wins":13},"gpt-5.4":{"draws":4,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":20,"losses":19,"wins":5},"gpt-5.4-nano":{"draws":13,"losses":24,"wins":15},"gpt-5.5":{"draws":18,"losses":16,"wins":10},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":7},"gpt-5.6-sol":{"draws":6,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":3},"gpt-6-astra":{"draws":4,"losses":12,"wins":0},"gpt-6-luna":{"draws":2,"losses":2,"wins":0},"gpt-6-sol":{"draws":6,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":1,"losses":8,"wins":5},"inclusionai/ling-3.0-flash":{"draws":20,"losses":0,"wins":18},"meituan/longcat-2.0":{"draws":13,"losses":8,"wins":25},"meta/muse-glimmer-30b":{"draws":6,"losses":2,"wins":6},"meta/muse-spark-1.2":{"draws":2,"losses":11,"wins":7},"meta/muse-spark-1.3":{"draws":6,"losses":7,"wins":1},"minimax/minimax-m3":{"draws":12,"losses":9,"wins":21},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":11,"wins":3},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":9,"wins":21},"o3":{"draws":8,"losses":14,"wins":16},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":12,"losses":10,"wins":14},"qwen/qwen3.7-max":{"draws":15,"losses":7,"wins":0},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":7,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":12,"wins":2},"qwen/qwen3.8-max":{"draws":8,"losses":3,"wins":3},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":0},"stealth/ox-alpha":{"draws":15,"losses":23,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":11},"tencent/hy3-preview":{"draws":20,"losses":6,"wins":12},"tencent/hy4-preview":{"draws":0,"losses":11,"wins":5},"thinkingmachines/inkling":{"draws":12,"losses":19,"wins":13},"thinkingmachines/inkling-small":{"draws":3,"losses":3,"wins":4},"x-ai/grok-4.5":{"draws":10,"losses":16,"wins":6},"x-ai/grok-4.6":{"draws":13,"losses":8,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":11,"losses":6,"wins":9},"xiaomi/mimo-v2.5":{"draws":40,"losses":20,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":5,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":17,"losses":27,"wins":18},"z-ai/glm-5.3":{"draws":1,"losses":7,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":5,"wins":2},"z-ai/glm-5.3-flashx":{"draws":8,"losses":8,"wins":4}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":4},"claude-opus-4-5":{"draws":2,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":2,"losses":3,"wins":1},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":7,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":5},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":14,"wins":17},"google/gemini-3.6-flash":{"draws":16,"losses":4,"wins":10},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":0,"losses":6,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":2},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":6,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":7,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":11},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":3},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":3},"meta/muse-spark-1.2":{"draws":2,"losses":7,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":8,"wins":16},"openai/gpt-oss-120b":{"draws":0,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.8-flash":{"draws":1,"losses":5,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":2},"stealth/ox-alpha":{"draws":1,"losses":16,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":12},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":6,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.3":{"draws":1,"losses":5,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.3-flashx":{"draws":0,"losses":2,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":13,"wins":17},"claude-fable-5":{"draws":11,"losses":21,"wins":10},"claude-fable-5-1":{"draws":1,"losses":44,"wins":1},"claude-opus-4-5":{"draws":49,"losses":39,"wins":40},"claude-opus-4-8":{"draws":23,"losses":56,"wins":27},"claude-opus-5":{"draws":24,"losses":144,"wins":14},"claude-opus-5-5":{"draws":0,"losses":16,"wins":2},"claude-sonnet-5":{"draws":13,"losses":9,"wins":10},"cohere/north-mini-code":{"draws":18,"losses":12,"wins":30},"deepseek/deepseek-v4-flash":{"draws":34,"losses":10,"wins":36},"deepseek/deepseek-v4-pro":{"draws":20,"losses":14,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":21,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":7,"wins":7},"google/gemini-3.1-flash-lite":{"draws":32,"losses":2,"wins":40},"google/gemini-3.5-flash":{"draws":16,"losses":26,"wins":20},"google/gemini-3.5-flash-lite":{"draws":41,"losses":22,"wins":29},"google/gemini-3.6-flash":{"draws":25,"losses":48,"wins":41},"google/gemini-3.8-flash":{"draws":13,"losses":25,"wins":14},"google/gemma-4-31b-it":{"draws":7,"losses":6,"wins":21},"gpt-4.1":{"draws":12,"losses":13,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":24,"losses":24,"wins":24},"gpt-5.4":{"draws":11,"losses":18,"wins":11},"gpt-5.4-mini":{"draws":32,"losses":23,"wins":21},"gpt-5.4-nano":{"draws":17,"losses":30,"wins":45},"gpt-5.5":{"draws":31,"losses":61,"wins":32},"gpt-5.6-luna":{"draws":3,"losses":6,"wins":19},"gpt-5.6-sol":{"draws":2,"losses":19,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":12,"wins":7},"gpt-6-astra":{"draws":0,"losses":20,"wins":0},"gpt-6-luna":{"draws":4,"losses":4,"wins":10},"gpt-6-sol":{"draws":1,"losses":15,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":9,"losses":2,"wins":13},"inclusionai/ling-3.0-flash":{"draws":19,"losses":22,"wins":21},"meituan/longcat-2.0":{"draws":34,"losses":22,"wins":46},"meta/muse-glimmer-30b":{"draws":9,"losses":5,"wins":20},"meta/muse-spark-1.2":{"draws":15,"losses":12,"wins":7},"meta/muse-spark-1.3":{"draws":9,"losses":19,"wins":8},"minimax/minimax-m3":{"draws":22,"losses":14,"wins":30},"mistralai/mistral-medium-3-5":{"draws":9,"losses":7,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":10,"wins":10},"moonshotai/kimi-k3":{"draws":18,"losses":17,"wins":15},"nex-agi/nex-n2-pro":{"draws":16,"losses":6,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":17,"wins":40},"o3":{"draws":28,"losses":32,"wins":54},"openai/gpt-oss-120b":{"draws":12,"losses":4,"wins":10},"poolside/laguna-s-2.1":{"draws":28,"losses":30,"wins":24},"qwen/qwen3.7-max":{"draws":27,"losses":15,"wins":28},"qwen/qwen3.7-plus":{"draws":14,"losses":9,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":16,"wins":12},"qwen/qwen3.8-27b":{"draws":3,"losses":13,"wins":12},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-max":{"draws":8,"losses":13,"wins":5},"qwen/qwen3.8-max-0902":{"draws":8,"losses":7,"wins":5},"stealth/ox-alpha":{"draws":36,"losses":56,"wins":32},"stepfun/step-3.7-flash":{"draws":24,"losses":5,"wins":31},"tencent/hy3-preview":{"draws":33,"losses":24,"wins":31},"tencent/hy4-preview":{"draws":17,"losses":12,"wins":9},"thinkingmachines/inkling":{"draws":30,"losses":24,"wins":42},"thinkingmachines/inkling-small":{"draws":12,"losses":2,"wins":18},"x-ai/grok-4.5":{"draws":18,"losses":41,"wins":13},"x-ai/grok-4.6":{"draws":12,"losses":14,"wins":8},"x-ai/grok-4.7":{"draws":0,"losses":10,"wins":2},"x-ai/grok-build-0.1":{"draws":15,"losses":10,"wins":17},"xiaomi/mimo-v2.5":{"draws":75,"losses":31,"wins":54},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":21,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":4,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":53,"losses":47,"wins":50},"z-ai/glm-5.3":{"draws":5,"losses":22,"wins":3},"z-ai/glm-5.3-flash":{"draws":18,"losses":18,"wins":10},"z-ai/glm-5.3-flashx":{"draws":12,"losses":6,"wins":2}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":25,"wins":33},"claude-fable-5":{"draws":37,"losses":60,"wins":47},"claude-fable-5-1":{"draws":12,"losses":124,"wins":20},"claude-opus-4-5":{"draws":58,"losses":42,"wins":112},"claude-opus-4-8":{"draws":5,"losses":13,"wins":10},"claude-opus-5":{"draws":5,"losses":55,"wins":6},"claude-opus-5-5":{"draws":2,"losses":19,"wins":3},"claude-sonnet-5":{"draws":83,"losses":51,"wins":152},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":49,"losses":23,"wins":70},"deepseek/deepseek-v4-pro":{"draws":42,"losses":33,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":44,"losses":31,"wins":45},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":8,"wins":22},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":25},"google/gemini-3.5-flash":{"draws":29,"losses":50,"wins":59},"google/gemini-3.5-flash-lite":{"draws":133,"losses":65,"wins":260},"google/gemini-3.6-flash":{"draws":111,"losses":133,"wins":196},"google/gemini-3.8-flash":{"draws":40,"losses":57,"wins":61},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":12},"gpt-4.1":{"draws":4,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":11,"losses":11,"wins":18},"gpt-5.4":{"draws":58,"losses":89,"wins":89},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":11},"gpt-5.4-nano":{"draws":5,"losses":12,"wins":23},"gpt-5.5":{"draws":16,"losses":17,"wins":17},"gpt-5.6-luna":{"draws":102,"losses":43,"wins":144},"gpt-5.6-sol":{"draws":59,"losses":136,"wins":95},"gpt-5.6-terra":{"draws":44,"losses":22,"wins":60},"gpt-6-astra":{"draws":14,"losses":109,"wins":19},"gpt-6-luna":{"draws":10,"losses":3,"wins":13},"gpt-6-sol":{"draws":3,"losses":24,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":13,"losses":2,"wins":7},"inception/mercury-2.5-preview":{"draws":43,"losses":2,"wins":27},"inclusionai/ling-3.0-flash":{"draws":16,"losses":13,"wins":41},"meituan/longcat-2.0":{"draws":52,"losses":23,"wins":78},"meta/muse-glimmer-30b":{"draws":36,"losses":18,"wins":38},"meta/muse-spark-1.2":{"draws":38,"losses":66,"wins":94},"meta/muse-spark-1.3":{"draws":25,"losses":47,"wins":48},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":10},"mistralai/mistral-medium-3-5":{"draws":29,"losses":11,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":9},"moonshotai/kimi-k3":{"draws":63,"losses":60,"wins":133},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":15},"o3":{"draws":30,"losses":55,"wins":185},"openai/gpt-oss-120b":{"draws":58,"losses":15,"wins":41},"poolside/laguna-s-2.1":{"draws":62,"losses":11,"wins":57},"qwen/qwen3.7-max":{"draws":3,"losses":8,"wins":9},"qwen/qwen3.7-plus":{"draws":3,"losses":4,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":34,"losses":62,"wins":50},"qwen/qwen3.8-27b":{"draws":21,"losses":15,"wins":38},"qwen/qwen3.8-flash":{"draws":22,"losses":26,"wins":28},"qwen/qwen3.8-max":{"draws":45,"losses":51,"wins":50},"qwen/qwen3.8-max-0902":{"draws":9,"losses":10,"wins":21},"stealth/ox-alpha":{"draws":148,"losses":135,"wins":176},"stepfun/step-3.7-flash":{"draws":13,"losses":9,"wins":40},"tencent/hy3-preview":{"draws":14,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":30,"losses":47,"wins":49},"thinkingmachines/inkling":{"draws":41,"losses":29,"wins":82},"thinkingmachines/inkling-small":{"draws":60,"losses":12,"wins":39},"x-ai/grok-4.5":{"draws":51,"losses":69,"wins":93},"x-ai/grok-4.6":{"draws":48,"losses":45,"wins":59},"x-ai/grok-4.7":{"draws":2,"losses":10,"wins":6},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":20,"losses":3,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":8,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":9,"wins":9},"z-ai/glm-5.2":{"draws":58,"losses":36,"wins":62},"z-ai/glm-5.3":{"draws":31,"losses":74,"wins":57},"z-ai/glm-5.3-flash":{"draws":31,"losses":45,"wins":56},"z-ai/glm-5.3-flashx":{"draws":7,"losses":7,"wins":6}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":10,"wins":6},"claude-fable-5":{"draws":9,"losses":14,"wins":3},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-opus-4-5":{"draws":59,"losses":59,"wins":42},"claude-opus-4-8":{"draws":28,"losses":43,"wins":29},"claude-opus-5":{"draws":27,"losses":85,"wins":10},"claude-opus-5-5":{"draws":2,"losses":18,"wins":0},"claude-sonnet-5":{"draws":10,"losses":11,"wins":9},"cohere/north-mini-code":{"draws":20,"losses":7,"wins":23},"deepseek/deepseek-v4-flash":{"draws":41,"losses":18,"wins":27},"deepseek/deepseek-v4-pro":{"draws":7,"losses":7,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":5,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":10,"wins":7},"google/gemini-3.1-flash-lite":{"draws":19,"losses":11,"wins":34},"google/gemini-3.5-flash":{"draws":14,"losses":21,"wins":9},"google/gemini-3.5-flash-lite":{"draws":30,"losses":26,"wins":38},"google/gemini-3.6-flash":{"draws":30,"losses":48,"wins":19},"google/gemini-3.8-flash":{"draws":6,"losses":15,"wins":9},"google/gemma-4-31b-it":{"draws":7,"losses":18,"wins":19},"gpt-4.1":{"draws":20,"losses":5,"wins":19},"gpt-5":{"draws":32,"losses":21,"wins":23},"gpt-5.4":{"draws":3,"losses":11,"wins":0},"gpt-5.4-mini":{"draws":20,"losses":14,"wins":14},"gpt-5.4-nano":{"draws":43,"losses":57,"wins":30},"gpt-5.5":{"draws":49,"losses":35,"wins":8},"gpt-5.6-luna":{"draws":6,"losses":6,"wins":2},"gpt-5.6-sol":{"draws":10,"losses":21,"wins":3},"gpt-5.6-terra":{"draws":12,"losses":14,"wins":4},"gpt-6-astra":{"draws":1,"losses":13,"wins":0},"gpt-6-luna":{"draws":4,"losses":5,"wins":3},"gpt-6-sol":{"draws":2,"losses":4,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":4,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":34,"losses":8,"wins":20},"meituan/longcat-2.0":{"draws":39,"losses":30,"wins":41},"meta/muse-glimmer-30b":{"draws":13,"losses":3,"wins":8},"meta/muse-spark-1.2":{"draws":2,"losses":11,"wins":9},"meta/muse-spark-1.3":{"draws":12,"losses":16,"wins":2},"minimax/minimax-m3":{"draws":22,"losses":26,"wins":30},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":15,"wins":6},"moonshotai/kimi-k3":{"draws":25,"losses":19,"wins":14},"nex-agi/nex-n2-pro":{"draws":27,"losses":13,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":58,"losses":25,"wins":27},"o3":{"draws":12,"losses":22,"wins":20},"openai/gpt-oss-120b":{"draws":6,"losses":6,"wins":6},"poolside/laguna-s-2.1":{"draws":44,"losses":18,"wins":24},"qwen/qwen3.7-max":{"draws":26,"losses":27,"wins":13},"qwen/qwen3.7-plus":{"draws":20,"losses":24,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":10,"wins":1},"qwen/qwen3.8-27b":{"draws":2,"losses":6,"wins":2},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":1},"qwen/qwen3.8-max":{"draws":12,"losses":11,"wins":9},"qwen/qwen3.8-max-0902":{"draws":4,"losses":6,"wins":4},"stealth/ox-alpha":{"draws":24,"losses":44,"wins":26},"stepfun/step-3.7-flash":{"draws":20,"losses":8,"wins":8},"tencent/hy3-preview":{"draws":18,"losses":13,"wins":11},"tencent/hy4-preview":{"draws":15,"losses":15,"wins":8},"thinkingmachines/inkling":{"draws":29,"losses":21,"wins":20},"thinkingmachines/inkling-small":{"draws":14,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":19,"losses":26,"wins":5},"x-ai/grok-4.6":{"draws":10,"losses":22,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":26,"losses":12,"wins":18},"xiaomi/mimo-v2.5":{"draws":80,"losses":43,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":17,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":9,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":10,"wins":1},"z-ai/glm-5.2":{"draws":71,"losses":41,"wins":20},"z-ai/glm-5.3":{"draws":7,"losses":22,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":10,"wins":2},"z-ai/glm-5.3-flashx":{"draws":3,"losses":14,"wins":5}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":11,"wins":13},"claude-fable-5":{"draws":3,"losses":28,"wins":7},"claude-fable-5-1":{"draws":0,"losses":22,"wins":0},"claude-opus-4-5":{"draws":55,"losses":94,"wins":71},"claude-opus-4-8":{"draws":35,"losses":86,"wins":35},"claude-opus-5":{"draws":26,"losses":162,"wins":24},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":6,"losses":12,"wins":14},"cohere/north-mini-code":{"draws":24,"losses":21,"wins":43},"deepseek/deepseek-v4-flash":{"draws":34,"losses":48,"wins":38},"deepseek/deepseek-v4-pro":{"draws":11,"losses":22,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":18,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":12,"wins":4},"google/gemini-3.1-flash-lite":{"draws":18,"losses":30,"wins":78},"google/gemini-3.5-flash":{"draws":19,"losses":45,"wins":18},"google/gemini-3.5-flash-lite":{"draws":33,"losses":54,"wins":33},"google/gemini-3.6-flash":{"draws":37,"losses":47,"wins":30},"google/gemini-3.8-flash":{"draws":7,"losses":27,"wins":6},"google/gemma-4-31b-it":{"draws":8,"losses":32,"wins":38},"gpt-4.1":{"draws":13,"losses":15,"wins":24},"gpt-4.1-nano":{"draws":3,"losses":2,"wins":1},"gpt-5":{"draws":17,"losses":45,"wins":30},"gpt-5.4":{"draws":5,"losses":23,"wins":12},"gpt-5.4-mini":{"draws":43,"losses":30,"wins":57},"gpt-5.4-nano":{"draws":42,"losses":63,"wins":63},"gpt-5.5":{"draws":47,"losses":73,"wins":44},"gpt-5.6-luna":{"draws":14,"losses":19,"wins":19},"gpt-5.6-sol":{"draws":5,"losses":30,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":18,"wins":14},"gpt-6-astra":{"draws":1,"losses":41,"wins":0},"gpt-6-luna":{"draws":12,"losses":8,"wins":8},"gpt-6-sol":{"draws":2,"losses":18,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":3},"inception/mercury-2.5-preview":{"draws":4,"losses":9,"wins":15},"inclusionai/ling-3.0-flash":{"draws":50,"losses":16,"wins":32},"meituan/longcat-2.0":{"draws":31,"losses":46,"wins":69},"meta/muse-glimmer-30b":{"draws":6,"losses":9,"wins":7},"meta/muse-spark-1.2":{"draws":2,"losses":9,"wins":7},"meta/muse-spark-1.3":{"draws":12,"losses":27,"wins":7},"minimax/minimax-m3":{"draws":32,"losses":29,"wins":41},"mistralai/mistral-medium-3-5":{"draws":5,"losses":8,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":14,"wins":16},"moonshotai/kimi-k3":{"draws":21,"losses":44,"wins":13},"nex-agi/nex-n2-pro":{"draws":22,"losses":28,"wins":40},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":37,"wins":40},"o3":{"draws":8,"losses":55,"wins":57},"openai/gpt-oss-120b":{"draws":0,"losses":17,"wins":9},"poolside/laguna-s-2.1":{"draws":48,"losses":48,"wins":34},"qwen/qwen3.7-max":{"draws":28,"losses":43,"wins":31},"qwen/qwen3.7-plus":{"draws":22,"losses":43,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":26,"wins":9},"qwen/qwen3.8-27b":{"draws":2,"losses":21,"wins":7},"qwen/qwen3.8-flash":{"draws":12,"losses":7,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":20,"wins":7},"qwen/qwen3.8-max-0902":{"draws":7,"losses":14,"wins":3},"stealth/ox-alpha":{"draws":21,"losses":77,"wins":20},"stepfun/step-3.7-flash":{"draws":28,"losses":20,"wins":46},"tencent/hy3-preview":{"draws":16,"losses":29,"wins":11},"tencent/hy4-preview":{"draws":8,"losses":23,"wins":7},"thinkingmachines/inkling":{"draws":17,"losses":27,"wins":48},"thinkingmachines/inkling-small":{"draws":15,"losses":15,"wins":12},"x-ai/grok-4.5":{"draws":13,"losses":46,"wins":29},"x-ai/grok-4.6":{"draws":10,"losses":23,"wins":9},"x-ai/grok-4.7":{"draws":6,"losses":17,"wins":1},"x-ai/grok-build-0.1":{"draws":13,"losses":18,"wins":35},"xiaomi/mimo-v2.5":{"draws":71,"losses":106,"wins":121},"xiaomi/mimo-v2.5-pro":{"draws":26,"losses":48,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":9,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":57,"losses":67,"wins":60},"z-ai/glm-5.3":{"draws":7,"losses":35,"wins":12},"z-ai/glm-5.3-flash":{"draws":3,"losses":16,"wins":3},"z-ai/glm-5.3-flashx":{"draws":8,"losses":18,"wins":10}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":10,"wins":16},"claude-fable-5":{"draws":7,"losses":18,"wins":11},"claude-fable-5-1":{"draws":4,"losses":35,"wins":5},"claude-opus-4-5":{"draws":83,"losses":48,"wins":69},"claude-opus-4-8":{"draws":42,"losses":40,"wins":60},"claude-opus-5":{"draws":35,"losses":169,"wins":78},"claude-opus-5-5":{"draws":0,"losses":14,"wins":4},"claude-sonnet-5":{"draws":13,"losses":3,"wins":20},"cohere/north-mini-code":{"draws":25,"losses":7,"wins":24},"deepseek/deepseek-v4-flash":{"draws":42,"losses":6,"wins":30},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":7,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":8,"wins":6},"google/gemini-3.1-flash-lite":{"draws":23,"losses":5,"wins":34},"google/gemini-3.5-flash":{"draws":20,"losses":12,"wins":20},"google/gemini-3.5-flash-lite":{"draws":49,"losses":11,"wins":30},"google/gemini-3.6-flash":{"draws":47,"losses":49,"wins":44},"google/gemini-3.8-flash":{"draws":8,"losses":10,"wins":16},"google/gemma-4-31b-it":{"draws":24,"losses":4,"wins":22},"gpt-4.1":{"draws":18,"losses":10,"wins":16},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":31,"losses":32,"wins":61},"gpt-5.4":{"draws":16,"losses":17,"wins":17},"gpt-5.4-mini":{"draws":49,"losses":8,"wins":35},"gpt-5.4-nano":{"draws":47,"losses":44,"wins":73},"gpt-5.5":{"draws":48,"losses":32,"wins":32},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":28},"gpt-5.6-sol":{"draws":15,"losses":6,"wins":15},"gpt-5.6-terra":{"draws":13,"losses":4,"wins":3},"gpt-6-astra":{"draws":2,"losses":24,"wins":2},"gpt-6-luna":{"draws":10,"losses":6,"wins":8},"gpt-6-sol":{"draws":5,"losses":21,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":8,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":47,"losses":5,"wins":30},"meituan/longcat-2.0":{"draws":52,"losses":24,"wins":35},"meta/muse-glimmer-30b":{"draws":20,"losses":2,"wins":20},"meta/muse-spark-1.2":{"draws":10,"losses":15,"wins":9},"meta/muse-spark-1.3":{"draws":5,"losses":8,"wins":9},"minimax/minimax-m3":{"draws":19,"losses":10,"wins":43},"mistralai/mistral-medium-3-5":{"draws":9,"losses":0,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":20,"losses":11,"wins":9},"moonshotai/kimi-k3":{"draws":24,"losses":24,"wins":12},"nex-agi/nex-n2-pro":{"draws":17,"losses":7,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":55,"losses":7,"wins":60},"o3":{"draws":26,"losses":15,"wins":53},"openai/gpt-oss-120b":{"draws":15,"losses":3,"wins":14},"poolside/laguna-s-2.1":{"draws":44,"losses":22,"wins":32},"qwen/qwen3.7-max":{"draws":34,"losses":20,"wins":28},"qwen/qwen3.7-plus":{"draws":37,"losses":10,"wins":33},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":1,"wins":14},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":13},"qwen/qwen3.8-flash":{"draws":11,"losses":5,"wins":16},"qwen/qwen3.8-max":{"draws":11,"losses":19,"wins":16},"qwen/qwen3.8-max-0902":{"draws":13,"losses":11,"wins":8},"stealth/ox-alpha":{"draws":33,"losses":43,"wins":26},"stepfun/step-3.7-flash":{"draws":10,"losses":11,"wins":45},"tencent/hy3-preview":{"draws":37,"losses":13,"wins":32},"tencent/hy4-preview":{"draws":15,"losses":11,"wins":10},"thinkingmachines/inkling":{"draws":32,"losses":23,"wins":57},"thinkingmachines/inkling-small":{"draws":7,"losses":4,"wins":21},"x-ai/grok-4.5":{"draws":33,"losses":41,"wins":26},"x-ai/grok-4.6":{"draws":13,"losses":10,"wins":7},"x-ai/grok-4.7":{"draws":1,"losses":15,"wins":12},"x-ai/grok-build-0.1":{"draws":34,"losses":7,"wins":9},"xiaomi/mimo-v2.5":{"draws":92,"losses":22,"wins":82},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":23,"wins":30},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":3,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":71,"losses":36,"wins":75},"z-ai/glm-5.3":{"draws":8,"losses":18,"wins":10},"z-ai/glm-5.3-flash":{"draws":8,"losses":16,"wins":14},"z-ai/glm-5.3-flashx":{"draws":16,"losses":4,"wins":8}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":50,"losses":52,"wins":42},"claude-fable-5":{"draws":32,"losses":52,"wins":20},"claude-fable-5-1":{"draws":10,"losses":82,"wins":4},"claude-opus-4-5":{"draws":85,"losses":88,"wins":55},"claude-opus-4-8":{"draws":9,"losses":17,"wins":4},"claude-opus-5":{"draws":8,"losses":62,"wins":10},"claude-opus-5-5":{"draws":1,"losses":11,"wins":0},"claude-sonnet-5":{"draws":99,"losses":115,"wins":80},"cohere/north-mini-code":{"draws":3,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":75,"losses":49,"wins":46},"deepseek/deepseek-v4-pro":{"draws":45,"losses":50,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":41,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":14,"losses":17,"wins":3},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":7},"google/gemini-3.5-flash":{"draws":55,"losses":51,"wins":32},"google/gemini-3.5-flash-lite":{"draws":174,"losses":160,"wins":200},"google/gemini-3.6-flash":{"draws":134,"losses":214,"wins":108},"google/gemini-3.8-flash":{"draws":33,"losses":67,"wins":32},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":8},"gpt-4.1":{"draws":3,"losses":7,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":6},"gpt-5":{"draws":3,"losses":19,"wins":6},"gpt-5.4":{"draws":102,"losses":144,"wins":43},"gpt-5.4-mini":{"draws":6,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":14,"losses":19,"wins":19},"gpt-5.5":{"draws":11,"losses":28,"wins":9},"gpt-5.6-luna":{"draws":104,"losses":53,"wins":53},"gpt-5.6-sol":{"draws":42,"losses":179,"wins":47},"gpt-5.6-terra":{"draws":49,"losses":45,"wins":54},"gpt-6-astra":{"draws":17,"losses":81,"wins":0},"gpt-6-luna":{"draws":8,"losses":14,"wins":4},"gpt-6-sol":{"draws":7,"losses":12,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":13,"losses":1,"wins":8},"inception/mercury-2.5-preview":{"draws":56,"losses":20,"wins":36},"inclusionai/ling-3.0-flash":{"draws":38,"losses":25,"wins":33},"meituan/longcat-2.0":{"draws":52,"losses":50,"wins":66},"meta/muse-glimmer-30b":{"draws":62,"losses":39,"wins":41},"meta/muse-spark-1.2":{"draws":50,"losses":100,"wins":52},"meta/muse-spark-1.3":{"draws":26,"losses":49,"wins":25},"minimax/minimax-m3":{"draws":7,"losses":6,"wins":9},"mistralai/mistral-medium-3-5":{"draws":41,"losses":13,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":5,"wins":3},"moonshotai/kimi-k3":{"draws":86,"losses":109,"wins":57},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":9,"wins":10},"o3":{"draws":38,"losses":129,"wins":115},"openai/gpt-oss-120b":{"draws":68,"losses":29,"wins":43},"poolside/laguna-s-2.1":{"draws":73,"losses":41,"wins":54},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":11,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":57,"losses":47,"wins":28},"qwen/qwen3.8-27b":{"draws":17,"losses":35,"wins":20},"qwen/qwen3.8-flash":{"draws":38,"losses":33,"wins":27},"qwen/qwen3.8-max":{"draws":55,"losses":62,"wins":27},"qwen/qwen3.8-max-0902":{"draws":12,"losses":18,"wins":2},"stealth/ox-alpha":{"draws":145,"losses":161,"wins":99},"stepfun/step-3.7-flash":{"draws":20,"losses":27,"wins":21},"tencent/hy3-preview":{"draws":2,"losses":6,"wins":10},"tencent/hy4-preview":{"draws":42,"losses":65,"wins":23},"thinkingmachines/inkling":{"draws":74,"losses":43,"wins":93},"thinkingmachines/inkling-small":{"draws":68,"losses":52,"wins":50},"x-ai/grok-4.5":{"draws":49,"losses":83,"wins":68},"x-ai/grok-4.6":{"draws":39,"losses":67,"wins":26},"x-ai/grok-4.7":{"draws":2,"losses":11,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":35,"losses":5,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":15,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":5,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":73,"losses":60,"wins":37},"z-ai/glm-5.3":{"draws":33,"losses":68,"wins":17},"z-ai/glm-5.3-flash":{"draws":38,"losses":49,"wins":35},"z-ai/glm-5.3-flashx":{"draws":3,"losses":13,"wins":4}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":16,"wins":68},"claude-fable-5":{"draws":21,"losses":73,"wins":70},"claude-fable-5-1":{"draws":17,"losses":144,"wins":27},"claude-opus-4-5":{"draws":39,"losses":48,"wins":169},"claude-opus-4-8":{"draws":20,"losses":15,"wins":17},"claude-opus-5":{"draws":15,"losses":80,"wins":15},"claude-opus-5-5":{"draws":1,"losses":19,"wins":2},"claude-sonnet-5":{"draws":49,"losses":43,"wins":237},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":21,"losses":19,"wins":98},"deepseek/deepseek-v4-pro":{"draws":15,"losses":36,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":29,"wins":75},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":7,"wins":9},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":16},"google/gemini-3.5-flash":{"draws":21,"losses":44,"wins":91},"google/gemini-3.5-flash-lite":{"draws":70,"losses":41,"wins":355},"google/gemini-3.6-flash":{"draws":61,"losses":134,"wins":245},"google/gemini-3.8-flash":{"draws":20,"losses":61,"wins":79},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":16},"gpt-4.1":{"draws":6,"losses":1,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":2,"losses":3,"wins":19},"gpt-5.4":{"draws":59,"losses":95,"wins":136},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":21},"gpt-5.4-nano":{"draws":5,"losses":3,"wins":30},"gpt-5.5":{"draws":15,"losses":15,"wins":6},"gpt-5.6-luna":{"draws":42,"losses":47,"wins":179},"gpt-5.6-sol":{"draws":28,"losses":96,"wins":96},"gpt-5.6-terra":{"draws":43,"losses":27,"wins":84},"gpt-6-astra":{"draws":15,"losses":143,"wins":16},"gpt-6-luna":{"draws":3,"losses":5,"wins":20},"gpt-6-sol":{"draws":2,"losses":13,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":18,"losses":1,"wins":45},"inclusionai/ling-3.0-flash":{"draws":12,"losses":6,"wins":56},"meituan/longcat-2.0":{"draws":23,"losses":15,"wins":122},"meta/muse-glimmer-30b":{"draws":13,"losses":7,"wins":48},"meta/muse-spark-1.2":{"draws":20,"losses":42,"wins":144},"meta/muse-spark-1.3":{"draws":29,"losses":46,"wins":65},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":10},"mistralai/mistral-medium-3-5":{"draws":12,"losses":4,"wins":48},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":61,"losses":52,"wins":145},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":5,"wins":20},"o3":{"draws":13,"losses":54,"wins":211},"openai/gpt-oss-120b":{"draws":13,"losses":8,"wins":67},"poolside/laguna-s-2.1":{"draws":33,"losses":3,"wins":134},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":7},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":43,"wins":86},"qwen/qwen3.8-27b":{"draws":13,"losses":23,"wins":46},"qwen/qwen3.8-flash":{"draws":21,"losses":22,"wins":53},"qwen/qwen3.8-max":{"draws":33,"losses":32,"wins":80},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":11},"stealth/ox-alpha":{"draws":72,"losses":141,"wins":282},"stepfun/step-3.7-flash":{"draws":2,"losses":12,"wins":38},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":24,"losses":49,"wins":77},"thinkingmachines/inkling":{"draws":27,"losses":12,"wins":125},"thinkingmachines/inkling-small":{"draws":18,"losses":18,"wins":75},"x-ai/grok-4.5":{"draws":27,"losses":79,"wins":122},"x-ai/grok-4.6":{"draws":31,"losses":67,"wins":70},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":10},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":7},"xiaomi/mimo-v2.5":{"draws":5,"losses":2,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":8,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":2,"wins":5},"z-ai/glm-5.2":{"draws":19,"losses":30,"wins":119},"z-ai/glm-5.3":{"draws":26,"losses":66,"wins":68},"z-ai/glm-5.3-flash":{"draws":30,"losses":57,"wins":77},"z-ai/glm-5.3-flashx":{"draws":7,"losses":7,"wins":6}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":24,"wins":56},"claude-fable-5":{"draws":39,"losses":88,"wins":23},"claude-fable-5-1":{"draws":13,"losses":126,"wins":3},"claude-opus-4-5":{"draws":47,"losses":52,"wins":31},"claude-opus-4-8":{"draws":11,"losses":26,"wins":7},"claude-opus-5":{"draws":11,"losses":50,"wins":3},"claude-opus-5-5":{"draws":2,"losses":22,"wins":0},"claude-sonnet-5":{"draws":49,"losses":40,"wins":53},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":26},"deepseek/deepseek-v4-flash":{"draws":62,"losses":35,"wins":67},"deepseek/deepseek-v4-pro":{"draws":44,"losses":49,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":45,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":9,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":35},"google/gemini-3.5-flash":{"draws":49,"losses":43,"wins":52},"google/gemini-3.5-flash-lite":{"draws":74,"losses":52,"wins":110},"google/gemini-3.6-flash":{"draws":66,"losses":88,"wins":60},"google/gemini-3.8-flash":{"draws":47,"losses":54,"wins":35},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":14},"gpt-4.1":{"draws":10,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":7},"gpt-5":{"draws":7,"losses":7,"wins":12},"gpt-5.4":{"draws":44,"losses":60,"wins":22},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":10,"losses":14,"wins":18},"gpt-5.5":{"draws":13,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":49,"losses":54,"wins":45},"gpt-5.6-sol":{"draws":43,"losses":84,"wins":27},"gpt-5.6-terra":{"draws":32,"losses":32,"wins":32},"gpt-6-astra":{"draws":11,"losses":126,"wins":7},"gpt-6-luna":{"draws":2,"losses":5,"wins":9},"gpt-6-sol":{"draws":2,"losses":11,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":44,"losses":11,"wins":47},"inclusionai/ling-3.0-flash":{"draws":16,"losses":4,"wins":36},"meituan/longcat-2.0":{"draws":30,"losses":23,"wins":43},"meta/muse-glimmer-30b":{"draws":57,"losses":18,"wins":49},"meta/muse-spark-1.2":{"draws":35,"losses":44,"wins":31},"meta/muse-spark-1.3":{"draws":33,"losses":68,"wins":39},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":10},"mistralai/mistral-medium-3-5":{"draws":27,"losses":10,"wins":43},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":49,"losses":54,"wins":37},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":6,"wins":24},"o3":{"draws":22,"losses":57,"wins":75},"openai/gpt-oss-120b":{"draws":45,"losses":13,"wins":72},"poolside/laguna-s-2.1":{"draws":43,"losses":11,"wins":38},"qwen/qwen3.7-max":{"draws":10,"losses":8,"wins":22},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":54,"losses":58,"wins":30},"qwen/qwen3.8-27b":{"draws":22,"losses":28,"wins":30},"qwen/qwen3.8-flash":{"draws":25,"losses":30,"wins":29},"qwen/qwen3.8-max":{"draws":63,"losses":44,"wins":35},"qwen/qwen3.8-max-0902":{"draws":11,"losses":10,"wins":1},"stealth/ox-alpha":{"draws":148,"losses":163,"wins":121},"stepfun/step-3.7-flash":{"draws":11,"losses":9,"wins":18},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":10},"tencent/hy4-preview":{"draws":36,"losses":50,"wins":36},"thinkingmachines/inkling":{"draws":30,"losses":17,"wins":53},"thinkingmachines/inkling-small":{"draws":49,"losses":26,"wins":67},"x-ai/grok-4.5":{"draws":32,"losses":72,"wins":26},"x-ai/grok-4.6":{"draws":48,"losses":83,"wins":25},"x-ai/grok-4.7":{"draws":3,"losses":10,"wins":3},"x-ai/grok-build-0.1":{"draws":7,"losses":4,"wins":9},"xiaomi/mimo-v2.5":{"draws":21,"losses":5,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":6,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":6},"z-ai/glm-5.2":{"draws":86,"losses":40,"wins":70},"z-ai/glm-5.3":{"draws":41,"losses":72,"wins":17},"z-ai/glm-5.3-flash":{"draws":37,"losses":60,"wins":33},"z-ai/glm-5.3-flashx":{"draws":5,"losses":5,"wins":10}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":10,"wins":59},"claude-fable-5":{"draws":12,"losses":33,"wins":119},"claude-fable-5-1":{"draws":18,"losses":66,"wins":110},"claude-opus-4-5":{"draws":14,"losses":8,"wins":132},"claude-opus-4-8":{"draws":6,"losses":1,"wins":43},"claude-opus-5":{"draws":10,"losses":19,"wins":51},"claude-opus-5-5":{"draws":2,"losses":11,"wins":15},"claude-sonnet-5":{"draws":7,"losses":10,"wins":131},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":16},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":104},"deepseek/deepseek-v4-pro":{"draws":4,"losses":12,"wins":88},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":1,"wins":106},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":2,"wins":26},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":24},"google/gemini-3.5-flash":{"draws":18,"losses":6,"wins":124},"google/gemini-3.5-flash-lite":{"draws":13,"losses":1,"wins":154},"google/gemini-3.6-flash":{"draws":21,"losses":15,"wins":168},"google/gemini-3.8-flash":{"draws":19,"losses":11,"wins":134},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":14},"gpt-4.1":{"draws":4,"losses":0,"wins":12},"gpt-5":{"draws":0,"losses":0,"wins":20},"gpt-5.4":{"draws":14,"losses":19,"wins":109},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":13},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":41},"gpt-5.5":{"draws":2,"losses":2,"wins":24},"gpt-5.6-luna":{"draws":17,"losses":0,"wins":81},"gpt-5.6-sol":{"draws":15,"losses":16,"wins":143},"gpt-5.6-terra":{"draws":11,"losses":7,"wins":126},"gpt-6-astra":{"draws":8,"losses":50,"wins":50},"gpt-6-luna":{"draws":6,"losses":2,"wins":16},"gpt-6-sol":{"draws":1,"losses":3,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":35},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":32},"meituan/longcat-2.0":{"draws":5,"losses":2,"wins":55},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":65},"meta/muse-spark-1.2":{"draws":12,"losses":2,"wins":84},"meta/muse-spark-1.3":{"draws":15,"losses":12,"wins":105},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":18},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":37},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":18,"losses":12,"wins":100},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":21},"o3":{"draws":1,"losses":1,"wins":122},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":53},"poolside/laguna-s-2.1":{"draws":16,"losses":0,"wins":56},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":21},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":7,"wins":113},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":78},"qwen/qwen3.8-flash":{"draws":11,"losses":2,"wins":67},"qwen/qwen3.8-max":{"draws":18,"losses":4,"wins":112},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":21},"stealth/ox-alpha":{"draws":67,"losses":33,"wins":392},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":26},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":12,"wins":107},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":72},"thinkingmachines/inkling-small":{"draws":9,"losses":0,"wins":83},"x-ai/grok-4.5":{"draws":6,"losses":11,"wins":99},"x-ai/grok-4.6":{"draws":13,"losses":16,"wins":139},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":11},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":7},"z-ai/glm-5.2":{"draws":11,"losses":4,"wins":123},"z-ai/glm-5.3":{"draws":23,"losses":13,"wins":116},"z-ai/glm-5.3-flash":{"draws":24,"losses":10,"wins":118},"z-ai/glm-5.3-flashx":{"draws":2,"losses":2,"wins":22}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":10,"wins":5},"claude-fable-5":{"draws":5,"losses":11,"wins":2},"claude-fable-5-1":{"draws":1,"losses":17,"wins":0},"claude-opus-4-5":{"draws":19,"losses":17,"wins":10},"claude-opus-4-8":{"draws":2,"losses":6,"wins":4},"claude-opus-5":{"draws":6,"losses":29,"wins":1},"claude-opus-5-5":{"draws":16,"losses":133,"wins":1},"claude-sonnet-5":{"draws":2,"losses":6,"wins":6},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":6,"losses":6,"wins":10},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":8,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":16,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":5,"wins":14},"google/gemini-3.5-flash":{"draws":8,"losses":20,"wins":12},"google/gemini-3.5-flash-lite":{"draws":10,"losses":11,"wins":31},"google/gemini-3.6-flash":{"draws":16,"losses":30,"wins":10},"google/gemini-3.8-flash":{"draws":6,"losses":10,"wins":4},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":10,"wins":4},"gpt-5.4":{"draws":10,"losses":13,"wins":3},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":12,"losses":8,"wins":8},"gpt-5.5":{"draws":10,"losses":8,"wins":6},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":14},"gpt-5.6-sol":{"draws":3,"losses":20,"wins":5},"gpt-5.6-terra":{"draws":2,"losses":9,"wins":5},"gpt-6-astra":{"draws":6,"losses":16,"wins":2},"gpt-6-luna":{"draws":20,"losses":34,"wins":34},"gpt-6-sol":{"draws":21,"losses":101,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":9,"losses":4,"wins":13},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":10},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":13},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":9},"meta/muse-spark-1.2":{"draws":2,"losses":7,"wins":3},"meta/muse-spark-1.3":{"draws":6,"losses":13,"wins":7},"minimax/minimax-m3":{"draws":6,"losses":1,"wins":7},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":10,"wins":6},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":3,"wins":9},"o3":{"draws":10,"losses":7,"wins":13},"openai/gpt-oss-120b":{"draws":9,"losses":6,"wins":9},"poolside/laguna-s-2.1":{"draws":11,"losses":8,"wins":11},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":10},"qwen/qwen3.7-plus":{"draws":3,"losses":4,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":13,"wins":5},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.8-flash":{"draws":0,"losses":7,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":14,"wins":5},"qwen/qwen3.8-max-0902":{"draws":23,"losses":10,"wins":15},"stealth/ox-alpha":{"draws":18,"losses":22,"wins":18},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":7},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":9},"tencent/hy4-preview":{"draws":2,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":12,"losses":3,"wins":9},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":7,"losses":11,"wins":6},"x-ai/grok-4.6":{"draws":4,"losses":10,"wins":4},"x-ai/grok-4.7":{"draws":8,"losses":61,"wins":15},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":10,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":16,"losses":19,"wins":23},"xiaomi/mimo-v2.6-pro":{"draws":19,"losses":36,"wins":17},"z-ai/glm-5.2":{"draws":12,"losses":20,"wins":14},"z-ai/glm-5.3":{"draws":4,"losses":11,"wins":3},"z-ai/glm-5.3-flash":{"draws":4,"losses":15,"wins":5},"z-ai/glm-5.3-flashx":{"draws":27,"losses":53,"wins":24}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":3,"wins":13},"claude-fable-5":{"draws":5,"losses":1,"wins":12},"claude-fable-5-1":{"draws":0,"losses":6,"wins":8},"claude-opus-4-5":{"draws":5,"losses":11,"wins":30},"claude-opus-4-8":{"draws":2,"losses":3,"wins":5},"claude-opus-5":{"draws":7,"losses":21,"wins":16},"claude-opus-5-5":{"draws":13,"losses":104,"wins":39},"claude-sonnet-5":{"draws":3,"losses":4,"wins":31},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":31},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":4,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":2,"wins":23},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":26},"google/gemini-3.5-flash":{"draws":7,"losses":7,"wins":22},"google/gemini-3.5-flash-lite":{"draws":9,"losses":8,"wins":53},"google/gemini-3.6-flash":{"draws":7,"losses":13,"wins":38},"google/gemini-3.8-flash":{"draws":2,"losses":4,"wins":12},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":4},"gpt-4.1":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":1,"losses":0,"wins":15},"gpt-5.4":{"draws":3,"losses":7,"wins":24},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":18},"gpt-5.5":{"draws":5,"losses":2,"wins":21},"gpt-5.6-luna":{"draws":7,"losses":1,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":13,"wins":13},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":11},"gpt-6-astra":{"draws":1,"losses":18,"wins":3},"gpt-6-luna":{"draws":21,"losses":16,"wins":101},"gpt-6-sol":{"draws":14,"losses":41,"wins":41},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":9},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":10},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":29},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":11},"meta/muse-spark-1.2":{"draws":3,"losses":2,"wins":13},"meta/muse-spark-1.3":{"draws":3,"losses":1,"wins":20},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":17},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":9,"wins":13},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":17},"o3":{"draws":2,"losses":1,"wins":19},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":12},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":19},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":9},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":5,"wins":11},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":7},"qwen/qwen3.8-flash":{"draws":2,"losses":1,"wins":7},"qwen/qwen3.8-max":{"draws":4,"losses":5,"wins":11},"qwen/qwen3.8-max-0902":{"draws":10,"losses":9,"wins":29},"stealth/ox-alpha":{"draws":13,"losses":12,"wins":51},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":17},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":18},"tencent/hy4-preview":{"draws":2,"losses":9,"wins":11},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":28},"thinkingmachines/inkling-small":{"draws":5,"losses":1,"wins":20},"x-ai/grok-4.5":{"draws":1,"losses":11,"wins":12},"x-ai/grok-4.6":{"draws":5,"losses":2,"wins":15},"x-ai/grok-4.7":{"draws":12,"losses":36,"wins":42},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":8,"losses":2,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":10,"losses":9,"wins":43},"xiaomi/mimo-v2.6-pro":{"draws":18,"losses":16,"wins":36},"z-ai/glm-5.2":{"draws":5,"losses":1,"wins":36},"z-ai/glm-5.3":{"draws":6,"losses":16,"wins":10},"z-ai/glm-5.3-flash":{"draws":6,"losses":9,"wins":15},"z-ai/glm-5.3-flashx":{"draws":20,"losses":29,"wins":65}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":13,"wins":0},"claude-fable-5":{"draws":4,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":2,"losses":14,"wins":0},"claude-opus-4-8":{"draws":6,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":12,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":16,"losses":8,"wins":0},"deepseek/deepseek-v4-pro":{"draws":8,"losses":8,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":8,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":7,"losses":11,"wins":0},"google/gemini-3.5-flash-lite":{"draws":25,"losses":9,"wins":0},"google/gemini-3.6-flash":{"draws":7,"losses":19,"wins":0},"google/gemini-3.8-flash":{"draws":3,"losses":13,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-4.1":{"draws":3,"losses":5,"wins":0},"gpt-5":{"draws":2,"losses":6,"wins":0},"gpt-5.4":{"draws":13,"losses":7,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":3,"wins":1},"gpt-5.5":{"draws":0,"losses":6,"wins":0},"gpt-5.6-luna":{"draws":13,"losses":8,"wins":1},"gpt-5.6-sol":{"draws":4,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":6,"losses":8,"wins":0},"gpt-6-astra":{"draws":0,"losses":10,"wins":0},"gpt-6-luna":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":8,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":4,"wins":0},"meituan/longcat-2.0":{"draws":5,"losses":5,"wins":2},"meta/muse-glimmer-30b":{"draws":16,"losses":8,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":9,"wins":0},"meta/muse-spark-1.3":{"draws":1,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":10,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":6,"losses":14,"wins":0},"openai/gpt-oss-120b":{"draws":12,"losses":12,"wins":0},"poolside/laguna-s-2.1":{"draws":8,"losses":4,"wins":2},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":8,"wins":1},"qwen/qwen3.8-27b":{"draws":6,"losses":4,"wins":0},"qwen/qwen3.8-flash":{"draws":5,"losses":2,"wins":1},"qwen/qwen3.8-max":{"draws":6,"losses":5,"wins":1},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":33,"losses":26,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":1,"losses":5,"wins":0},"tencent/hy4-preview":{"draws":5,"losses":9,"wins":0},"thinkingmachines/inkling":{"draws":6,"losses":10,"wins":0},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":3,"wins":0},"x-ai/grok-4.6":{"draws":6,"losses":10,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":16,"losses":8,"wins":2},"z-ai/glm-5.3":{"draws":6,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":2,"wins":0},"z-ai/glm-5.3-flashx":{"draws":0,"losses":4,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":48,"losses":35,"wins":29},"claude-fable-5":{"draws":24,"losses":37,"wins":3},"claude-fable-5-1":{"draws":5,"losses":39,"wins":0},"claude-opus-4-5":{"draws":41,"losses":56,"wins":7},"claude-opus-4-8":{"draws":6,"losses":18,"wins":4},"claude-opus-5":{"draws":9,"losses":32,"wins":1},"claude-opus-5-5":{"draws":4,"losses":18,"wins":0},"claude-sonnet-5":{"draws":51,"losses":52,"wins":9},"cohere/north-mini-code":{"draws":8,"losses":10,"wins":12},"deepseek/deepseek-v4-flash":{"draws":56,"losses":51,"wins":13},"deepseek/deepseek-v4-pro":{"draws":45,"losses":37,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":43,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":12,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":38,"losses":41,"wins":7},"google/gemini-3.5-flash-lite":{"draws":96,"losses":80,"wins":36},"google/gemini-3.6-flash":{"draws":64,"losses":82,"wins":14},"google/gemini-3.8-flash":{"draws":37,"losses":40,"wins":3},"google/gemma-4-31b-it":{"draws":3,"losses":12,"wins":7},"gpt-4.1":{"draws":1,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":9,"losses":13,"wins":2},"gpt-5.4":{"draws":43,"losses":27,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":4},"gpt-5.4-nano":{"draws":4,"losses":15,"wins":9},"gpt-5.5":{"draws":8,"losses":12,"wins":2},"gpt-5.6-luna":{"draws":56,"losses":36,"wins":20},"gpt-5.6-sol":{"draws":18,"losses":45,"wins":1},"gpt-5.6-terra":{"draws":44,"losses":47,"wins":11},"gpt-6-astra":{"draws":7,"losses":35,"wins":0},"gpt-6-luna":{"draws":9,"losses":13,"wins":4},"gpt-6-sol":{"draws":1,"losses":9,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":36,"losses":10,"wins":10},"inclusionai/ling-3.0-flash":{"draws":19,"losses":13,"wins":8},"meituan/longcat-2.0":{"draws":27,"losses":29,"wins":17},"meta/muse-glimmer-30b":{"draws":55,"losses":30,"wins":21},"meta/muse-spark-1.2":{"draws":28,"losses":42,"wins":6},"meta/muse-spark-1.3":{"draws":25,"losses":35,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":4},"mistralai/mistral-medium-3-5":{"draws":37,"losses":20,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":44,"losses":46,"wins":6},"nex-agi/nex-n2-pro":{"draws":11,"losses":8,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":6,"wins":9},"o3":{"draws":22,"losses":63,"wins":17},"openai/gpt-oss-120b":{"draws":53,"losses":31,"wins":24},"poolside/laguna-s-2.1":{"draws":28,"losses":23,"wins":17},"qwen/qwen3.7-max":{"draws":12,"losses":6,"wins":6},"qwen/qwen3.7-plus":{"draws":12,"losses":12,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":43,"wins":8},"qwen/qwen3.8-27b":{"draws":13,"losses":35,"wins":6},"qwen/qwen3.8-flash":{"draws":35,"losses":32,"wins":7},"qwen/qwen3.8-max":{"draws":48,"losses":37,"wins":11},"qwen/qwen3.8-max-0902":{"draws":7,"losses":11,"wins":0},"stealth/ox-alpha":{"draws":99,"losses":136,"wins":38},"stepfun/step-3.7-flash":{"draws":11,"losses":21,"wins":6},"tencent/hy3-preview":{"draws":13,"losses":5,"wins":8},"tencent/hy4-preview":{"draws":40,"losses":44,"wins":8},"thinkingmachines/inkling":{"draws":48,"losses":23,"wins":11},"thinkingmachines/inkling-small":{"draws":63,"losses":38,"wins":29},"x-ai/grok-4.5":{"draws":36,"losses":41,"wins":3},"x-ai/grok-4.6":{"draws":31,"losses":35,"wins":12},"x-ai/grok-4.7":{"draws":1,"losses":10,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":22,"losses":15,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":7,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":63,"losses":67,"wins":20},"z-ai/glm-5.3":{"draws":30,"losses":34,"wins":4},"z-ai/glm-5.3-flash":{"draws":35,"losses":43,"wins":10},"z-ai/glm-5.3-flashx":{"draws":7,"losses":9,"wins":0}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":20,"wins":9},"claude-fable-5":{"draws":7,"losses":18,"wins":1},"claude-fable-5-1":{"draws":0,"losses":38,"wins":0},"claude-opus-4-5":{"draws":50,"losses":57,"wins":23},"claude-opus-4-8":{"draws":37,"losses":29,"wins":0},"claude-opus-5":{"draws":25,"losses":66,"wins":5},"claude-opus-5-5":{"draws":2,"losses":20,"wins":0},"claude-sonnet-5":{"draws":28,"losses":66,"wins":12},"cohere/north-mini-code":{"draws":29,"losses":9,"wins":20},"deepseek/deepseek-v4-flash":{"draws":49,"losses":42,"wins":33},"deepseek/deepseek-v4-pro":{"draws":15,"losses":27,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":12,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":18,"wins":2},"google/gemini-3.1-flash-lite":{"draws":19,"losses":26,"wins":19},"google/gemini-3.5-flash":{"draws":25,"losses":34,"wins":5},"google/gemini-3.5-flash-lite":{"draws":92,"losses":127,"wins":47},"google/gemini-3.6-flash":{"draws":118,"losses":109,"wins":39},"google/gemini-3.8-flash":{"draws":13,"losses":33,"wins":2},"google/gemma-4-31b-it":{"draws":16,"losses":25,"wins":13},"gpt-4.1":{"draws":20,"losses":18,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":11,"wins":1},"gpt-5":{"draws":19,"losses":21,"wins":22},"gpt-5.4":{"draws":16,"losses":41,"wins":13},"gpt-5.4-mini":{"draws":34,"losses":20,"wins":8},"gpt-5.4-nano":{"draws":50,"losses":32,"wins":16},"gpt-5.5":{"draws":47,"losses":30,"wins":5},"gpt-5.6-luna":{"draws":38,"losses":33,"wins":25},"gpt-5.6-sol":{"draws":12,"losses":56,"wins":6},"gpt-5.6-terra":{"draws":16,"losses":36,"wins":4},"gpt-6-astra":{"draws":2,"losses":32,"wins":0},"gpt-6-luna":{"draws":8,"losses":10,"wins":2},"gpt-6-sol":{"draws":1,"losses":10,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":19,"losses":8,"wins":13},"inclusionai/ling-3.0-flash":{"draws":30,"losses":31,"wins":31},"meituan/longcat-2.0":{"draws":80,"losses":65,"wins":45},"meta/muse-glimmer-30b":{"draws":26,"losses":19,"wins":11},"meta/muse-spark-1.2":{"draws":22,"losses":19,"wins":13},"meta/muse-spark-1.3":{"draws":8,"losses":27,"wins":7},"minimax/minimax-m3":{"draws":35,"losses":28,"wins":17},"mistralai/mistral-medium-3-5":{"draws":20,"losses":16,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":10,"wins":4},"moonshotai/kimi-k3":{"draws":43,"losses":65,"wins":20},"nex-agi/nex-n2-pro":{"draws":34,"losses":21,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":23,"wins":21},"o3":{"draws":23,"losses":90,"wins":37},"openai/gpt-oss-120b":{"draws":12,"losses":36,"wins":8},"poolside/laguna-s-2.1":{"draws":82,"losses":48,"wins":20},"qwen/qwen3.7-max":{"draws":35,"losses":28,"wins":7},"qwen/qwen3.7-plus":{"draws":28,"losses":16,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":37,"wins":3},"qwen/qwen3.8-27b":{"draws":10,"losses":22,"wins":6},"qwen/qwen3.8-flash":{"draws":18,"losses":27,"wins":9},"qwen/qwen3.8-max":{"draws":27,"losses":29,"wins":9},"qwen/qwen3.8-max-0902":{"draws":11,"losses":20,"wins":1},"stealth/ox-alpha":{"draws":36,"losses":70,"wins":24},"stepfun/step-3.7-flash":{"draws":20,"losses":26,"wins":10},"tencent/hy3-preview":{"draws":15,"losses":22,"wins":5},"tencent/hy4-preview":{"draws":11,"losses":27,"wins":6},"thinkingmachines/inkling":{"draws":61,"losses":52,"wins":47},"thinkingmachines/inkling-small":{"draws":23,"losses":29,"wins":13},"x-ai/grok-4.5":{"draws":42,"losses":87,"wins":15},"x-ai/grok-4.6":{"draws":16,"losses":21,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":15,"losses":20,"wins":1},"xiaomi/mimo-v2.5":{"draws":59,"losses":46,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":26,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":9,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":62,"losses":31,"wins":17},"z-ai/glm-5.3":{"draws":15,"losses":25,"wins":0},"z-ai/glm-5.3-flash":{"draws":9,"losses":25,"wins":6},"z-ai/glm-5.3-flashx":{"draws":8,"losses":20,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":30,"losses":31,"wins":21},"claude-fable-5":{"draws":11,"losses":42,"wins":22},"claude-fable-5-1":{"draws":1,"losses":50,"wins":3},"claude-opus-4-5":{"draws":68,"losses":133,"wins":48},"claude-opus-4-8":{"draws":15,"losses":40,"wins":19},"claude-opus-5":{"draws":20,"losses":152,"wins":20},"claude-opus-5-5":{"draws":0,"losses":19,"wins":1},"claude-sonnet-5":{"draws":53,"losses":88,"wins":17},"cohere/north-mini-code":{"draws":35,"losses":8,"wins":33},"deepseek/deepseek-v4-flash":{"draws":53,"losses":51,"wins":34},"deepseek/deepseek-v4-pro":{"draws":25,"losses":48,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":39,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":26,"wins":10},"google/gemini-3.1-flash-lite":{"draws":15,"losses":26,"wins":43},"google/gemini-3.5-flash":{"draws":26,"losses":74,"wins":22},"google/gemini-3.5-flash-lite":{"draws":111,"losses":178,"wins":155},"google/gemini-3.6-flash":{"draws":115,"losses":203,"wins":71},"google/gemini-3.8-flash":{"draws":20,"losses":39,"wins":10},"google/gemma-4-31b-it":{"draws":15,"losses":28,"wins":31},"gpt-4.1":{"draws":13,"losses":25,"wins":8},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":34,"losses":46,"wins":22},"gpt-5.4":{"draws":52,"losses":78,"wins":23},"gpt-5.4-mini":{"draws":39,"losses":41,"wins":30},"gpt-5.4-nano":{"draws":31,"losses":69,"wins":46},"gpt-5.5":{"draws":52,"losses":35,"wins":24},"gpt-5.6-luna":{"draws":52,"losses":66,"wins":50},"gpt-5.6-sol":{"draws":23,"losses":122,"wins":15},"gpt-5.6-terra":{"draws":30,"losses":43,"wins":23},"gpt-6-astra":{"draws":5,"losses":55,"wins":2},"gpt-6-luna":{"draws":6,"losses":13,"wins":3},"gpt-6-sol":{"draws":2,"losses":29,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":2,"wins":5},"inception/mercury-2.5-preview":{"draws":27,"losses":17,"wins":29},"inclusionai/ling-3.0-flash":{"draws":80,"losses":45,"wins":65},"meituan/longcat-2.0":{"draws":44,"losses":53,"wins":53},"meta/muse-glimmer-30b":{"draws":34,"losses":32,"wins":26},"meta/muse-spark-1.2":{"draws":36,"losses":49,"wins":39},"meta/muse-spark-1.3":{"draws":25,"losses":53,"wins":12},"minimax/minimax-m3":{"draws":14,"losses":25,"wins":25},"mistralai/mistral-medium-3-5":{"draws":26,"losses":17,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":14,"wins":4},"moonshotai/kimi-k3":{"draws":69,"losses":117,"wins":30},"nex-agi/nex-n2-pro":{"draws":15,"losses":18,"wins":33},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":37,"losses":26,"wins":19},"o3":{"draws":38,"losses":152,"wins":78},"openai/gpt-oss-120b":{"draws":36,"losses":29,"wins":35},"poolside/laguna-s-2.1":{"draws":94,"losses":68,"wins":74},"qwen/qwen3.7-max":{"draws":27,"losses":34,"wins":6},"qwen/qwen3.7-plus":{"draws":17,"losses":17,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":52,"wins":13},"qwen/qwen3.8-27b":{"draws":15,"losses":32,"wins":13},"qwen/qwen3.8-flash":{"draws":30,"losses":24,"wins":10},"qwen/qwen3.8-max":{"draws":36,"losses":42,"wins":18},"qwen/qwen3.8-max-0902":{"draws":12,"losses":30,"wins":7},"stealth/ox-alpha":{"draws":69,"losses":173,"wins":44},"stepfun/step-3.7-flash":{"draws":23,"losses":47,"wins":40},"tencent/hy3-preview":{"draws":28,"losses":23,"wins":23},"tencent/hy4-preview":{"draws":22,"losses":47,"wins":13},"thinkingmachines/inkling":{"draws":54,"losses":92,"wins":68},"thinkingmachines/inkling-small":{"draws":31,"losses":32,"wins":38},"x-ai/grok-4.5":{"draws":53,"losses":130,"wins":43},"x-ai/grok-4.6":{"draws":24,"losses":38,"wins":16},"x-ai/grok-4.7":{"draws":2,"losses":16,"wins":2},"x-ai/grok-build-0.1":{"draws":16,"losses":23,"wins":17},"xiaomi/mimo-v2.5":{"draws":73,"losses":65,"wins":74},"xiaomi/mimo-v2.5-pro":{"draws":32,"losses":34,"wins":26},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":1,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":7,"wins":1},"z-ai/glm-5.2":{"draws":64,"losses":84,"wins":60},"z-ai/glm-5.3":{"draws":24,"losses":50,"wins":6},"z-ai/glm-5.3-flash":{"draws":24,"losses":43,"wins":23},"z-ai/glm-5.3-flashx":{"draws":17,"losses":11,"wins":5}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":59,"losses":47,"wins":36},"claude-fable-5":{"draws":28,"losses":38,"wins":8},"claude-fable-5-1":{"draws":6,"losses":60,"wins":0},"claude-opus-4-5":{"draws":41,"losses":58,"wins":13},"claude-opus-4-8":{"draws":9,"losses":16,"wins":5},"claude-opus-5":{"draws":5,"losses":35,"wins":6},"claude-opus-5-5":{"draws":2,"losses":28,"wins":0},"claude-sonnet-5":{"draws":49,"losses":59,"wins":18},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":16},"deepseek/deepseek-v4-flash":{"draws":76,"losses":49,"wins":27},"deepseek/deepseek-v4-pro":{"draws":45,"losses":47,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":54,"losses":55,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":18,"wins":3},"google/gemini-3.1-flash-lite":{"draws":16,"losses":5,"wins":9},"google/gemini-3.5-flash":{"draws":36,"losses":51,"wins":27},"google/gemini-3.5-flash-lite":{"draws":100,"losses":84,"wins":56},"google/gemini-3.6-flash":{"draws":92,"losses":95,"wins":31},"google/gemini-3.8-flash":{"draws":36,"losses":47,"wins":15},"google/gemma-4-31b-it":{"draws":2,"losses":6,"wins":6},"gpt-4.1":{"draws":6,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":3,"wins":1},"gpt-5":{"draws":9,"losses":20,"wins":5},"gpt-5.4":{"draws":36,"losses":38,"wins":18},"gpt-5.4-mini":{"draws":13,"losses":8,"wins":3},"gpt-5.4-nano":{"draws":6,"losses":7,"wins":9},"gpt-5.5":{"draws":20,"losses":20,"wins":2},"gpt-5.6-luna":{"draws":62,"losses":41,"wins":39},"gpt-5.6-sol":{"draws":13,"losses":48,"wins":7},"gpt-5.6-terra":{"draws":57,"losses":49,"wins":18},"gpt-6-astra":{"draws":5,"losses":65,"wins":0},"gpt-6-luna":{"draws":7,"losses":9,"wins":4},"gpt-6-sol":{"draws":3,"losses":11,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":16,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":55,"losses":21,"wins":30},"inclusionai/ling-3.0-flash":{"draws":26,"losses":11,"wins":19},"meituan/longcat-2.0":{"draws":34,"losses":26,"wins":32},"meta/muse-glimmer-30b":{"draws":40,"losses":20,"wins":20},"meta/muse-spark-1.2":{"draws":21,"losses":41,"wins":20},"meta/muse-spark-1.3":{"draws":37,"losses":29,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":6},"mistralai/mistral-medium-3-5":{"draws":48,"losses":11,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":9,"wins":3},"moonshotai/kimi-k3":{"draws":40,"losses":43,"wins":17},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":5,"wins":10},"o3":{"draws":31,"losses":64,"wins":23},"openai/gpt-oss-120b":{"draws":57,"losses":36,"wins":33},"poolside/laguna-s-2.1":{"draws":50,"losses":25,"wins":19},"qwen/qwen3.7-max":{"draws":9,"losses":11,"wins":6},"qwen/qwen3.7-plus":{"draws":11,"losses":7,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":49,"losses":40,"wins":17},"qwen/qwen3.8-27b":{"draws":24,"losses":39,"wins":9},"qwen/qwen3.8-flash":{"draws":38,"losses":16,"wins":22},"qwen/qwen3.8-max":{"draws":36,"losses":46,"wins":32},"qwen/qwen3.8-max-0902":{"draws":17,"losses":13,"wins":0},"stealth/ox-alpha":{"draws":119,"losses":198,"wins":57},"stepfun/step-3.7-flash":{"draws":14,"losses":7,"wins":17},"tencent/hy3-preview":{"draws":7,"losses":10,"wins":3},"tencent/hy4-preview":{"draws":44,"losses":49,"wins":13},"thinkingmachines/inkling":{"draws":48,"losses":28,"wins":34},"thinkingmachines/inkling-small":{"draws":72,"losses":26,"wins":54},"x-ai/grok-4.5":{"draws":27,"losses":47,"wins":12},"x-ai/grok-4.6":{"draws":42,"losses":40,"wins":12},"x-ai/grok-4.7":{"draws":0,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":34,"losses":13,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":6,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":74,"losses":59,"wins":33},"z-ai/glm-5.3":{"draws":17,"losses":39,"wins":12},"z-ai/glm-5.3-flash":{"draws":40,"losses":59,"wins":13},"z-ai/glm-5.3-flashx":{"draws":9,"losses":7,"wins":4}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":24,"wins":31},"claude-fable-5":{"draws":18,"losses":47,"wins":27},"claude-fable-5-1":{"draws":10,"losses":95,"wins":9},"claude-opus-4-5":{"draws":47,"losses":48,"wins":73},"claude-opus-4-8":{"draws":14,"losses":23,"wins":11},"claude-opus-5":{"draws":4,"losses":40,"wins":12},"claude-opus-5-5":{"draws":0,"losses":12,"wins":2},"claude-sonnet-5":{"draws":63,"losses":75,"wins":74},"cohere/north-mini-code":{"draws":1,"losses":6,"wins":23},"deepseek/deepseek-v4-flash":{"draws":22,"losses":19,"wins":45},"deepseek/deepseek-v4-pro":{"draws":14,"losses":39,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":32,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":9,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":12},"google/gemini-3.5-flash":{"draws":25,"losses":51,"wins":36},"google/gemini-3.5-flash-lite":{"draws":89,"losses":72,"wins":177},"google/gemini-3.6-flash":{"draws":64,"losses":130,"wins":154},"google/gemini-3.8-flash":{"draws":19,"losses":40,"wins":43},"google/gemma-4-31b-it":{"draws":11,"losses":1,"wins":14},"gpt-4.1":{"draws":2,"losses":7,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":3,"wins":7},"gpt-5":{"draws":15,"losses":7,"wins":12},"gpt-5.4":{"draws":38,"losses":94,"wins":66},"gpt-5.4-mini":{"draws":2,"losses":9,"wins":11},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":9},"gpt-5.5":{"draws":10,"losses":9,"wins":15},"gpt-5.6-luna":{"draws":50,"losses":52,"wins":100},"gpt-5.6-sol":{"draws":20,"losses":144,"wins":42},"gpt-5.6-terra":{"draws":35,"losses":31,"wins":44},"gpt-6-astra":{"draws":12,"losses":84,"wins":2},"gpt-6-luna":{"draws":2,"losses":3,"wins":7},"gpt-6-sol":{"draws":3,"losses":13,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":9},"inception/mercury-2.5-preview":{"draws":28,"losses":6,"wins":42},"inclusionai/ling-3.0-flash":{"draws":22,"losses":13,"wins":19},"meituan/longcat-2.0":{"draws":36,"losses":39,"wins":49},"meta/muse-glimmer-30b":{"draws":21,"losses":20,"wins":41},"meta/muse-spark-1.2":{"draws":22,"losses":41,"wins":41},"meta/muse-spark-1.3":{"draws":23,"losses":38,"wins":27},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":41,"losses":77,"wins":62},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":3,"wins":15},"o3":{"draws":12,"losses":99,"wins":91},"openai/gpt-oss-120b":{"draws":27,"losses":9,"wins":44},"poolside/laguna-s-2.1":{"draws":36,"losses":21,"wins":65},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":14},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":47,"wins":29},"qwen/qwen3.8-27b":{"draws":11,"losses":29,"wins":24},"qwen/qwen3.8-flash":{"draws":23,"losses":25,"wins":22},"qwen/qwen3.8-max":{"draws":29,"losses":38,"wins":36},"qwen/qwen3.8-max-0902":{"draws":8,"losses":14,"wins":6},"stealth/ox-alpha":{"draws":90,"losses":187,"wins":106},"stepfun/step-3.7-flash":{"draws":2,"losses":11,"wins":33},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":15},"tencent/hy4-preview":{"draws":22,"losses":49,"wins":33},"thinkingmachines/inkling":{"draws":47,"losses":21,"wins":72},"thinkingmachines/inkling-small":{"draws":32,"losses":24,"wins":56},"x-ai/grok-4.5":{"draws":33,"losses":83,"wins":40},"x-ai/grok-4.6":{"draws":23,"losses":64,"wins":21},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":6},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":11,"losses":8,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":18,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":1},"z-ai/glm-5.2":{"draws":31,"losses":53,"wins":66},"z-ai/glm-5.3":{"draws":21,"losses":57,"wins":24},"z-ai/glm-5.3-flash":{"draws":16,"losses":45,"wins":39},"z-ai/glm-5.3-flashx":{"draws":5,"losses":9,"wins":10}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":19,"wins":50},"claude-fable-5":{"draws":20,"losses":65,"wins":43},"claude-fable-5-1":{"draws":4,"losses":127,"wins":7},"claude-opus-4-5":{"draws":25,"losses":33,"wins":68},"claude-opus-4-8":{"draws":9,"losses":15,"wins":14},"claude-opus-5":{"draws":16,"losses":66,"wins":14},"claude-opus-5-5":{"draws":2,"losses":18,"wins":2},"claude-sonnet-5":{"draws":48,"losses":34,"wins":50},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":36,"losses":25,"wins":77},"deepseek/deepseek-v4-pro":{"draws":22,"losses":39,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":30,"losses":30,"wins":58},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":4,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":16},"google/gemini-3.5-flash":{"draws":23,"losses":40,"wins":73},"google/gemini-3.5-flash-lite":{"draws":42,"losses":45,"wins":113},"google/gemini-3.6-flash":{"draws":36,"losses":71,"wins":93},"google/gemini-3.8-flash":{"draws":20,"losses":45,"wins":57},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":15},"gpt-4.1":{"draws":6,"losses":1,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":2},"gpt-5":{"draws":9,"losses":8,"wins":19},"gpt-5.4":{"draws":25,"losses":48,"wins":47},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":16},"gpt-5.4-nano":{"draws":12,"losses":7,"wins":27},"gpt-5.5":{"draws":5,"losses":9,"wins":8},"gpt-5.6-luna":{"draws":26,"losses":25,"wins":49},"gpt-5.6-sol":{"draws":29,"losses":65,"wins":46},"gpt-5.6-terra":{"draws":33,"losses":39,"wins":68},"gpt-6-astra":{"draws":15,"losses":105,"wins":12},"gpt-6-luna":{"draws":6,"losses":7,"wins":13},"gpt-6-sol":{"draws":3,"losses":20,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":9},"inception/mercury-2.5-preview":{"draws":25,"losses":6,"wins":35},"inclusionai/ling-3.0-flash":{"draws":8,"losses":7,"wins":27},"meituan/longcat-2.0":{"draws":25,"losses":12,"wins":53},"meta/muse-glimmer-30b":{"draws":37,"losses":10,"wins":29},"meta/muse-spark-1.2":{"draws":23,"losses":27,"wins":38},"meta/muse-spark-1.3":{"draws":14,"losses":27,"wins":27},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":15},"mistralai/mistral-medium-3-5":{"draws":21,"losses":4,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":34,"losses":46,"wins":62},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":5,"wins":22},"o3":{"draws":12,"losses":38,"wins":94},"openai/gpt-oss-120b":{"draws":30,"losses":14,"wins":56},"poolside/laguna-s-2.1":{"draws":26,"losses":15,"wins":37},"qwen/qwen3.7-max":{"draws":6,"losses":8,"wins":10},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":41,"losses":47,"wins":50},"qwen/qwen3.8-27b":{"draws":13,"losses":25,"wins":34},"qwen/qwen3.8-flash":{"draws":27,"losses":22,"wins":43},"qwen/qwen3.8-max":{"draws":27,"losses":25,"wins":62},"qwen/qwen3.8-max-0902":{"draws":13,"losses":6,"wins":9},"stealth/ox-alpha":{"draws":103,"losses":160,"wins":160},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":36},"tencent/hy3-preview":{"draws":2,"losses":4,"wins":20},"tencent/hy4-preview":{"draws":26,"losses":52,"wins":40},"thinkingmachines/inkling":{"draws":25,"losses":10,"wins":35},"thinkingmachines/inkling-small":{"draws":44,"losses":13,"wins":61},"x-ai/grok-4.5":{"draws":12,"losses":45,"wins":45},"x-ai/grok-4.6":{"draws":31,"losses":57,"wins":52},"x-ai/grok-4.7":{"draws":3,"losses":15,"wins":4},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":5,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":5,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":4},"z-ai/glm-5.2":{"draws":36,"losses":37,"wins":51},"z-ai/glm-5.3":{"draws":28,"losses":77,"wins":33},"z-ai/glm-5.3-flash":{"draws":28,"losses":55,"wins":43},"z-ai/glm-5.3-flashx":{"draws":13,"losses":8,"wins":3}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":21,"wins":9},"claude-fable-5":{"draws":5,"losses":15,"wins":2},"claude-fable-5-1":{"draws":1,"losses":20,"wins":1},"claude-opus-4-5":{"draws":28,"losses":59,"wins":13},"claude-opus-4-8":{"draws":22,"losses":44,"wins":12},"claude-opus-5":{"draws":12,"losses":86,"wins":10},"claude-opus-5-5":{"draws":2,"losses":15,"wins":1},"claude-sonnet-5":{"draws":3,"losses":15,"wins":4},"cohere/north-mini-code":{"draws":8,"losses":15,"wins":33},"deepseek/deepseek-v4-flash":{"draws":32,"losses":30,"wins":30},"deepseek/deepseek-v4-pro":{"draws":4,"losses":7,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":14,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":5,"wins":3},"google/gemini-3.1-flash-lite":{"draws":20,"losses":30,"wins":32},"google/gemini-3.5-flash":{"draws":16,"losses":14,"wins":10},"google/gemini-3.5-flash-lite":{"draws":21,"losses":25,"wins":22},"google/gemini-3.6-flash":{"draws":17,"losses":39,"wins":10},"google/gemini-3.8-flash":{"draws":8,"losses":17,"wins":1},"google/gemma-4-31b-it":{"draws":12,"losses":14,"wins":20},"gpt-4.1":{"draws":12,"losses":21,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":22,"losses":30,"wins":14},"gpt-5.4":{"draws":4,"losses":10,"wins":6},"gpt-5.4-mini":{"draws":22,"losses":30,"wins":26},"gpt-5.4-nano":{"draws":32,"losses":41,"wins":29},"gpt-5.5":{"draws":19,"losses":43,"wins":10},"gpt-5.6-luna":{"draws":7,"losses":9,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":10,"wins":0},"gpt-5.6-terra":{"draws":8,"losses":10,"wins":6},"gpt-6-astra":{"draws":0,"losses":18,"wins":0},"gpt-6-luna":{"draws":6,"losses":7,"wins":1},"gpt-6-sol":{"draws":1,"losses":17,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":6,"losses":4,"wins":12},"inclusionai/ling-3.0-flash":{"draws":35,"losses":17,"wins":28},"meituan/longcat-2.0":{"draws":14,"losses":25,"wins":25},"meta/muse-glimmer-30b":{"draws":7,"losses":6,"wins":9},"meta/muse-spark-1.2":{"draws":5,"losses":10,"wins":1},"meta/muse-spark-1.3":{"draws":4,"losses":15,"wins":1},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":1,"losses":4,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":15,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":20,"wins":4},"nex-agi/nex-n2-pro":{"draws":16,"losses":13,"wins":29},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":25,"wins":30},"o3":{"draws":11,"losses":34,"wins":11},"openai/gpt-oss-120b":{"draws":8,"losses":14,"wins":4},"poolside/laguna-s-2.1":{"draws":26,"losses":26,"wins":22},"qwen/qwen3.7-max":{"draws":29,"losses":33,"wins":14},"qwen/qwen3.7-plus":{"draws":13,"losses":20,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":14,"wins":3},"qwen/qwen3.8-27b":{"draws":3,"losses":7,"wins":2},"qwen/qwen3.8-flash":{"draws":11,"losses":10,"wins":9},"qwen/qwen3.8-max":{"draws":9,"losses":7,"wins":4},"qwen/qwen3.8-max-0902":{"draws":6,"losses":3,"wins":5},"stealth/ox-alpha":{"draws":28,"losses":40,"wins":10},"stepfun/step-3.7-flash":{"draws":13,"losses":10,"wins":17},"tencent/hy3-preview":{"draws":25,"losses":27,"wins":12},"tencent/hy4-preview":{"draws":4,"losses":14,"wins":2},"thinkingmachines/inkling":{"draws":18,"losses":32,"wins":28},"thinkingmachines/inkling-small":{"draws":4,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":8,"losses":34,"wins":4},"x-ai/grok-4.6":{"draws":7,"losses":13,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":5,"wins":0},"x-ai/grok-build-0.1":{"draws":16,"losses":19,"wins":9},"xiaomi/mimo-v2.5":{"draws":65,"losses":58,"wins":51},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":23,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":7,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":5,"wins":0},"z-ai/glm-5.2":{"draws":37,"losses":32,"wins":19},"z-ai/glm-5.3":{"draws":3,"losses":10,"wins":1},"z-ai/glm-5.3-flash":{"draws":7,"losses":12,"wins":3},"z-ai/glm-5.3-flashx":{"draws":1,"losses":15,"wins":2}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":38,"losses":25,"wins":19},"claude-fable-5":{"draws":24,"losses":22,"wins":8},"claude-fable-5-1":{"draws":2,"losses":40,"wins":0},"claude-opus-4-5":{"draws":18,"losses":51,"wins":9},"claude-opus-4-8":{"draws":6,"losses":16,"wins":0},"claude-opus-5":{"draws":9,"losses":25,"wins":4},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":40,"losses":37,"wins":13},"cohere/north-mini-code":{"draws":3,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":41,"losses":31,"wins":16},"deepseek/deepseek-v4-pro":{"draws":27,"losses":40,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":41,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":6,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":23,"losses":39,"wins":14},"google/gemini-3.5-flash-lite":{"draws":60,"losses":68,"wins":34},"google/gemini-3.6-flash":{"draws":44,"losses":56,"wins":18},"google/gemini-3.8-flash":{"draws":21,"losses":32,"wins":5},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":4},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":9,"losses":4,"wins":7},"gpt-5.4":{"draws":29,"losses":16,"wins":11},"gpt-5.4-mini":{"draws":7,"losses":5,"wins":0},"gpt-5.4-nano":{"draws":5,"losses":7,"wins":8},"gpt-5.5":{"draws":9,"losses":9,"wins":0},"gpt-5.6-luna":{"draws":41,"losses":34,"wins":13},"gpt-5.6-sol":{"draws":12,"losses":48,"wins":4},"gpt-5.6-terra":{"draws":27,"losses":43,"wins":10},"gpt-6-astra":{"draws":1,"losses":37,"wins":0},"gpt-6-luna":{"draws":3,"losses":3,"wins":0},"gpt-6-sol":{"draws":3,"losses":11,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":37,"losses":21,"wins":20},"inclusionai/ling-3.0-flash":{"draws":20,"losses":8,"wins":16},"meituan/longcat-2.0":{"draws":26,"losses":24,"wins":17},"meta/muse-glimmer-30b":{"draws":48,"losses":33,"wins":11},"meta/muse-spark-1.2":{"draws":21,"losses":35,"wins":8},"meta/muse-spark-1.3":{"draws":21,"losses":31,"wins":4},"minimax/minimax-m3":{"draws":1,"losses":7,"wins":4},"mistralai/mistral-medium-3-5":{"draws":16,"losses":8,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":25,"losses":38,"wins":7},"nex-agi/nex-n2-pro":{"draws":12,"losses":6,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":9,"wins":3},"o3":{"draws":15,"losses":53,"wins":10},"openai/gpt-oss-120b":{"draws":39,"losses":21,"wins":14},"poolside/laguna-s-2.1":{"draws":31,"losses":26,"wins":15},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":55,"wins":3},"qwen/qwen3.8-27b":{"draws":9,"losses":27,"wins":6},"qwen/qwen3.8-flash":{"draws":24,"losses":26,"wins":8},"qwen/qwen3.8-max":{"draws":29,"losses":41,"wins":10},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":0},"stealth/ox-alpha":{"draws":74,"losses":122,"wins":44},"stepfun/step-3.7-flash":{"draws":8,"losses":9,"wins":7},"tencent/hy3-preview":{"draws":8,"losses":3,"wins":1},"tencent/hy4-preview":{"draws":31,"losses":39,"wins":6},"thinkingmachines/inkling":{"draws":26,"losses":29,"wins":13},"thinkingmachines/inkling-small":{"draws":49,"losses":34,"wins":19},"x-ai/grok-4.5":{"draws":17,"losses":35,"wins":8},"x-ai/grok-4.6":{"draws":26,"losses":28,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":5,"wins":1},"xiaomi/mimo-v2.5":{"draws":10,"losses":6,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":9,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":5,"wins":0},"z-ai/glm-5.2":{"draws":52,"losses":53,"wins":19},"z-ai/glm-5.3":{"draws":23,"losses":28,"wins":7},"z-ai/glm-5.3-flash":{"draws":23,"losses":31,"wins":14},"z-ai/glm-5.3-flashx":{"draws":7,"losses":8,"wins":3}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":7},"claude-fable-5":{"draws":4,"losses":0,"wins":2},"claude-fable-5-1":{"draws":2,"losses":10,"wins":0},"claude-opus-4-5":{"draws":13,"losses":30,"wins":21},"claude-opus-4-8":{"draws":10,"losses":15,"wins":9},"claude-opus-5":{"draws":10,"losses":66,"wins":2},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":4,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":11},"deepseek/deepseek-v4-flash":{"draws":12,"losses":10,"wins":14},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":6,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":5},"google/gemini-3.5-flash-lite":{"draws":8,"losses":11,"wins":5},"google/gemini-3.6-flash":{"draws":6,"losses":20,"wins":4},"google/gemini-3.8-flash":{"draws":3,"losses":4,"wins":1},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":22},"gpt-4.1":{"draws":8,"losses":5,"wins":7},"gpt-5":{"draws":10,"losses":10,"wins":10},"gpt-5.4":{"draws":1,"losses":9,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":6,"losses":16,"wins":14},"gpt-5.5":{"draws":20,"losses":9,"wins":11},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":4},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":2,"losses":0,"wins":0},"gpt-6-sol":{"draws":3,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":14},"meta/muse-glimmer-30b":{"draws":2,"losses":3,"wins":9},"meta/muse-spark-1.2":{"draws":5,"losses":4,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":10,"losses":3,"wins":15},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":4,"wins":18},"o3":{"draws":2,"losses":9,"wins":13},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":3},"poolside/laguna-s-2.1":{"draws":12,"losses":17,"wins":3},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":15,"losses":2,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.8-max":{"draws":2,"losses":6,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":4},"stealth/ox-alpha":{"draws":5,"losses":10,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":5,"wins":8},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":2,"losses":6,"wins":2},"thinkingmachines/inkling":{"draws":6,"losses":13,"wins":15},"thinkingmachines/inkling-small":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":1},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":15},"xiaomi/mimo-v2.5":{"draws":33,"losses":13,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":0,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":20,"wins":19},"z-ai/glm-5.3":{"draws":2,"losses":2,"wins":2},"z-ai/glm-5.3-flashx":{"draws":7,"losses":1,"wins":6}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":21,"wins":46},"claude-fable-5":{"draws":26,"losses":84,"wins":20},"claude-fable-5-1":{"draws":14,"losses":130,"wins":4},"claude-opus-4-5":{"draws":101,"losses":68,"wins":101},"claude-opus-4-8":{"draws":19,"losses":18,"wins":29},"claude-opus-5":{"draws":22,"losses":114,"wins":26},"claude-opus-5-5":{"draws":1,"losses":19,"wins":6},"claude-sonnet-5":{"draws":87,"losses":59,"wins":114},"cohere/north-mini-code":{"draws":8,"losses":4,"wins":18},"deepseek/deepseek-v4-flash":{"draws":49,"losses":42,"wins":59},"deepseek/deepseek-v4-pro":{"draws":41,"losses":31,"wins":38},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":35,"wins":32},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":12,"wins":6},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":17},"google/gemini-3.5-flash":{"draws":61,"losses":53,"wins":30},"google/gemini-3.5-flash-lite":{"draws":190,"losses":108,"wins":260},"google/gemini-3.6-flash":{"draws":156,"losses":215,"wins":177},"google/gemini-3.8-flash":{"draws":50,"losses":60,"wins":32},"google/gemma-4-31b-it":{"draws":9,"losses":6,"wins":33},"gpt-4.1":{"draws":8,"losses":3,"wins":11},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":18,"losses":15,"wins":17},"gpt-5.4":{"draws":63,"losses":133,"wins":60},"gpt-5.4-mini":{"draws":25,"losses":14,"wins":19},"gpt-5.4-nano":{"draws":21,"losses":13,"wins":44},"gpt-5.5":{"draws":24,"losses":12,"wins":24},"gpt-5.6-luna":{"draws":86,"losses":57,"wins":109},"gpt-5.6-sol":{"draws":61,"losses":145,"wins":52},"gpt-5.6-terra":{"draws":49,"losses":37,"wins":54},"gpt-6-astra":{"draws":18,"losses":100,"wins":12},"gpt-6-luna":{"draws":4,"losses":6,"wins":10},"gpt-6-sol":{"draws":4,"losses":13,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":44,"losses":6,"wins":46},"inclusionai/ling-3.0-flash":{"draws":43,"losses":20,"wins":65},"meituan/longcat-2.0":{"draws":69,"losses":30,"wins":117},"meta/muse-glimmer-30b":{"draws":40,"losses":17,"wins":43},"meta/muse-spark-1.2":{"draws":41,"losses":62,"wins":77},"meta/muse-spark-1.3":{"draws":34,"losses":62,"wins":46},"minimax/minimax-m3":{"draws":12,"losses":4,"wins":20},"mistralai/mistral-medium-3-5":{"draws":25,"losses":7,"wins":38},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":84,"losses":62,"wins":62},"nex-agi/nex-n2-pro":{"draws":9,"losses":5,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":3,"wins":14},"o3":{"draws":40,"losses":133,"wins":137},"openai/gpt-oss-120b":{"draws":39,"losses":16,"wins":61},"poolside/laguna-s-2.1":{"draws":90,"losses":23,"wins":95},"qwen/qwen3.7-max":{"draws":14,"losses":10,"wins":20},"qwen/qwen3.7-plus":{"draws":13,"losses":6,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":50,"losses":48,"wins":50},"qwen/qwen3.8-27b":{"draws":22,"losses":19,"wins":25},"qwen/qwen3.8-flash":{"draws":36,"losses":19,"wins":27},"qwen/qwen3.8-max":{"draws":37,"losses":41,"wins":43},"qwen/qwen3.8-max-0902":{"draws":10,"losses":14,"wins":4},"stealth/ox-alpha":{"draws":115,"losses":176,"wins":140},"stepfun/step-3.7-flash":{"draws":20,"losses":11,"wins":49},"tencent/hy3-preview":{"draws":15,"losses":3,"wins":14},"tencent/hy4-preview":{"draws":41,"losses":35,"wins":48},"thinkingmachines/inkling":{"draws":94,"losses":27,"wins":111},"thinkingmachines/inkling-small":{"draws":53,"losses":17,"wins":64},"x-ai/grok-4.5":{"draws":86,"losses":108,"wins":82},"x-ai/grok-4.6":{"draws":46,"losses":59,"wins":33},"x-ai/grok-4.7":{"draws":6,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":10,"losses":4,"wins":16},"xiaomi/mimo-v2.5":{"draws":29,"losses":12,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":20,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":5,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":68,"losses":35,"wins":55},"z-ai/glm-5.3":{"draws":31,"losses":72,"wins":27},"z-ai/glm-5.3-flash":{"draws":49,"losses":50,"wins":33},"z-ai/glm-5.3-flashx":{"draws":10,"losses":11,"wins":9}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":15,"wins":2},"claude-fable-5":{"draws":2,"losses":9,"wins":1},"claude-fable-5-1":{"draws":2,"losses":20,"wins":0},"claude-opus-4-5":{"draws":17,"losses":52,"wins":15},"claude-opus-4-8":{"draws":31,"losses":39,"wins":8},"claude-opus-5":{"draws":1,"losses":57,"wins":6},"claude-opus-5-5":{"draws":2,"losses":12,"wins":0},"claude-sonnet-5":{"draws":9,"losses":13,"wins":4},"cohere/north-mini-code":{"draws":17,"losses":13,"wins":24},"deepseek/deepseek-v4-flash":{"draws":18,"losses":32,"wins":26},"deepseek/deepseek-v4-pro":{"draws":6,"losses":12,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":13,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":14,"losses":20,"wins":28},"google/gemini-3.5-flash":{"draws":9,"losses":13,"wins":10},"google/gemini-3.5-flash-lite":{"draws":26,"losses":12,"wins":8},"google/gemini-3.6-flash":{"draws":18,"losses":41,"wins":13},"google/gemini-3.8-flash":{"draws":4,"losses":13,"wins":3},"google/gemma-4-31b-it":{"draws":8,"losses":17,"wins":17},"gpt-4.1":{"draws":6,"losses":8,"wins":8},"gpt-5":{"draws":16,"losses":28,"wins":6},"gpt-5.4":{"draws":3,"losses":11,"wins":2},"gpt-5.4-mini":{"draws":27,"losses":20,"wins":13},"gpt-5.4-nano":{"draws":22,"losses":40,"wins":28},"gpt-5.5":{"draws":17,"losses":50,"wins":7},"gpt-5.6-luna":{"draws":5,"losses":11,"wins":4},"gpt-5.6-sol":{"draws":3,"losses":21,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":4},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"gpt-6-luna":{"draws":0,"losses":8,"wins":0},"gpt-6-sol":{"draws":0,"losses":4,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":5,"wins":8},"inclusionai/ling-3.0-flash":{"draws":34,"losses":19,"wins":21},"meituan/longcat-2.0":{"draws":15,"losses":33,"wins":18},"meta/muse-glimmer-30b":{"draws":7,"losses":10,"wins":5},"meta/muse-spark-1.2":{"draws":5,"losses":13,"wins":6},"meta/muse-spark-1.3":{"draws":4,"losses":11,"wins":1},"minimax/minimax-m3":{"draws":16,"losses":29,"wins":13},"mistralai/mistral-medium-3-5":{"draws":12,"losses":10,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":12,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":22,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":44,"losses":36,"wins":18},"o3":{"draws":7,"losses":37,"wins":10},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":1},"poolside/laguna-s-2.1":{"draws":24,"losses":21,"wins":9},"qwen/qwen3.7-max":{"draws":17,"losses":27,"wins":6},"qwen/qwen3.7-plus":{"draws":18,"losses":19,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":17,"wins":5},"qwen/qwen3.8-27b":{"draws":2,"losses":19,"wins":7},"qwen/qwen3.8-flash":{"draws":16,"losses":18,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":14,"wins":2},"qwen/qwen3.8-max-0902":{"draws":0,"losses":6,"wins":4},"stealth/ox-alpha":{"draws":17,"losses":42,"wins":11},"stepfun/step-3.7-flash":{"draws":15,"losses":13,"wins":18},"tencent/hy3-preview":{"draws":26,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":4,"losses":16,"wins":0},"thinkingmachines/inkling":{"draws":16,"losses":20,"wins":22},"thinkingmachines/inkling-small":{"draws":7,"losses":8,"wins":7},"x-ai/grok-4.5":{"draws":16,"losses":35,"wins":1},"x-ai/grok-4.6":{"draws":7,"losses":15,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":9,"wins":1},"x-ai/grok-build-0.1":{"draws":16,"losses":12,"wins":6},"xiaomi/mimo-v2.5":{"draws":31,"losses":50,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":22,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":46,"losses":35,"wins":15},"z-ai/glm-5.3":{"draws":3,"losses":16,"wins":1},"z-ai/glm-5.3-flash":{"draws":3,"losses":12,"wins":3},"z-ai/glm-5.3-flashx":{"draws":0,"losses":9,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":17,"wins":13},"claude-fable-5":{"draws":10,"losses":21,"wins":3},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-opus-4-5":{"draws":67,"losses":72,"wins":29},"claude-opus-4-8":{"draws":23,"losses":70,"wins":15},"claude-opus-5":{"draws":32,"losses":121,"wins":3},"claude-opus-5-5":{"draws":0,"losses":28,"wins":0},"claude-sonnet-5":{"draws":19,"losses":19,"wins":10},"cohere/north-mini-code":{"draws":24,"losses":20,"wins":10},"deepseek/deepseek-v4-flash":{"draws":52,"losses":37,"wins":27},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":17,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":38,"losses":29,"wins":42},"google/gemini-3.5-flash":{"draws":20,"losses":12,"wins":8},"google/gemini-3.5-flash-lite":{"draws":42,"losses":33,"wins":27},"google/gemini-3.6-flash":{"draws":31,"losses":54,"wins":9},"google/gemini-3.8-flash":{"draws":13,"losses":15,"wins":4},"google/gemma-4-31b-it":{"draws":19,"losses":23,"wins":8},"gpt-4.1":{"draws":18,"losses":21,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":43,"losses":40,"wins":17},"gpt-5.4":{"draws":6,"losses":15,"wins":3},"gpt-5.4-mini":{"draws":58,"losses":27,"wins":25},"gpt-5.4-nano":{"draws":45,"losses":40,"wins":37},"gpt-5.5":{"draws":55,"losses":60,"wins":7},"gpt-5.6-luna":{"draws":7,"losses":10,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":20,"wins":5},"gpt-5.6-terra":{"draws":18,"losses":24,"wins":6},"gpt-6-astra":{"draws":1,"losses":21,"wins":0},"gpt-6-luna":{"draws":12,"losses":9,"wins":3},"gpt-6-sol":{"draws":5,"losses":17,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":9,"wins":6},"inclusionai/ling-3.0-flash":{"draws":36,"losses":21,"wins":23},"meituan/longcat-2.0":{"draws":37,"losses":19,"wins":26},"meta/muse-glimmer-30b":{"draws":15,"losses":10,"wins":5},"meta/muse-spark-1.2":{"draws":10,"losses":15,"wins":3},"meta/muse-spark-1.3":{"draws":11,"losses":22,"wins":5},"minimax/minimax-m3":{"draws":31,"losses":30,"wins":25},"mistralai/mistral-medium-3-5":{"draws":10,"losses":3,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":20,"losses":18,"wins":4},"moonshotai/kimi-k3":{"draws":19,"losses":14,"wins":3},"nex-agi/nex-n2-pro":{"draws":44,"losses":18,"wins":36},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":58,"losses":19,"wins":19},"o3":{"draws":36,"losses":55,"wins":21},"openai/gpt-oss-120b":{"draws":11,"losses":15,"wins":10},"poolside/laguna-s-2.1":{"draws":43,"losses":22,"wins":15},"qwen/qwen3.7-max":{"draws":49,"losses":24,"wins":15},"qwen/qwen3.7-plus":{"draws":40,"losses":20,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":11,"wins":5},"qwen/qwen3.8-27b":{"draws":6,"losses":7,"wins":3},"qwen/qwen3.8-flash":{"draws":14,"losses":13,"wins":9},"qwen/qwen3.8-max":{"draws":7,"losses":19,"wins":6},"qwen/qwen3.8-max-0902":{"draws":9,"losses":16,"wins":3},"stealth/ox-alpha":{"draws":24,"losses":57,"wins":9},"stepfun/step-3.7-flash":{"draws":34,"losses":20,"wins":24},"tencent/hy3-preview":{"draws":49,"losses":25,"wins":14},"tencent/hy4-preview":{"draws":18,"losses":19,"wins":3},"thinkingmachines/inkling":{"draws":50,"losses":35,"wins":41},"thinkingmachines/inkling-small":{"draws":15,"losses":11,"wins":10},"x-ai/grok-4.5":{"draws":21,"losses":45,"wins":2},"x-ai/grok-4.6":{"draws":14,"losses":12,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":8,"wins":2},"x-ai/grok-build-0.1":{"draws":45,"losses":8,"wins":9},"xiaomi/mimo-v2.5":{"draws":112,"losses":60,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":26,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":3},"z-ai/glm-5.2":{"draws":90,"losses":51,"wins":29},"z-ai/glm-5.3":{"draws":6,"losses":25,"wins":7},"z-ai/glm-5.3-flash":{"draws":9,"losses":16,"wins":3},"z-ai/glm-5.3-flashx":{"draws":8,"losses":14,"wins":4}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":24,"losses":43,"wins":69},"claude-fable-5":{"draws":11,"losses":105,"wins":20},"claude-fable-5-1":{"draws":0,"losses":118,"wins":6},"claude-opus-4-5":{"draws":60,"losses":221,"wins":107},"claude-opus-4-8":{"draws":11,"losses":72,"wins":25},"claude-opus-5":{"draws":4,"losses":159,"wins":9},"claude-opus-5-5":{"draws":1,"losses":29,"wins":2},"claude-sonnet-5":{"draws":26,"losses":153,"wins":135},"cohere/north-mini-code":{"draws":25,"losses":16,"wins":23},"deepseek/deepseek-v4-flash":{"draws":32,"losses":72,"wins":92},"deepseek/deepseek-v4-pro":{"draws":27,"losses":77,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":66,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":20,"wins":9},"google/gemini-3.1-flash-lite":{"draws":12,"losses":5,"wins":61},"google/gemini-3.5-flash":{"draws":24,"losses":93,"wins":53},"google/gemini-3.5-flash-lite":{"draws":111,"losses":230,"wins":383},"google/gemini-3.6-flash":{"draws":112,"losses":329,"wins":221},"google/gemini-3.8-flash":{"draws":18,"losses":90,"wins":40},"google/gemma-4-31b-it":{"draws":12,"losses":9,"wins":31},"gpt-4.1":{"draws":8,"losses":16,"wins":14},"gpt-4.1-nano":{"draws":0,"losses":16,"wins":8},"gpt-5":{"draws":28,"losses":54,"wins":32},"gpt-5.4":{"draws":30,"losses":185,"wins":55},"gpt-5.4-mini":{"draws":12,"losses":20,"wins":22},"gpt-5.4-nano":{"draws":8,"losses":57,"wins":55},"gpt-5.5":{"draws":26,"losses":53,"wins":15},"gpt-5.6-luna":{"draws":38,"losses":115,"wins":129},"gpt-5.6-sol":{"draws":13,"losses":211,"wins":54},"gpt-5.6-terra":{"draws":22,"losses":75,"wins":57},"gpt-6-astra":{"draws":1,"losses":122,"wins":1},"gpt-6-luna":{"draws":10,"losses":13,"wins":7},"gpt-6-sol":{"draws":2,"losses":19,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":14},"inception/mercury-2.5-preview":{"draws":22,"losses":17,"wins":63},"inclusionai/ling-3.0-flash":{"draws":23,"losses":37,"wins":90},"meituan/longcat-2.0":{"draws":38,"losses":78,"wins":152},"meta/muse-glimmer-30b":{"draws":31,"losses":23,"wins":64},"meta/muse-spark-1.2":{"draws":12,"losses":91,"wins":99},"meta/muse-spark-1.3":{"draws":12,"losses":94,"wins":38},"minimax/minimax-m3":{"draws":11,"losses":11,"wins":34},"mistralai/mistral-medium-3-5":{"draws":15,"losses":10,"wins":53},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":13,"wins":9},"moonshotai/kimi-k3":{"draws":40,"losses":137,"wins":133},"nex-agi/nex-n2-pro":{"draws":7,"losses":10,"wins":37},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":21,"wins":55},"o3":{"draws":44,"losses":204,"wins":204},"openai/gpt-oss-120b":{"draws":29,"losses":31,"wins":72},"poolside/laguna-s-2.1":{"draws":59,"losses":59,"wins":86},"qwen/qwen3.7-max":{"draws":18,"losses":15,"wins":29},"qwen/qwen3.7-plus":{"draws":8,"losses":18,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":80,"wins":46},"qwen/qwen3.8-27b":{"draws":23,"losses":60,"wins":33},"qwen/qwen3.8-flash":{"draws":28,"losses":35,"wins":41},"qwen/qwen3.8-max":{"draws":28,"losses":84,"wins":48},"qwen/qwen3.8-max-0902":{"draws":5,"losses":16,"wins":7},"stealth/ox-alpha":{"draws":54,"losses":209,"wins":181},"stepfun/step-3.7-flash":{"draws":37,"losses":51,"wins":104},"tencent/hy3-preview":{"draws":24,"losses":21,"wins":25},"tencent/hy4-preview":{"draws":24,"losses":74,"wins":52},"thinkingmachines/inkling":{"draws":61,"losses":67,"wins":163},"thinkingmachines/inkling-small":{"draws":56,"losses":49,"wins":72},"x-ai/grok-4.5":{"draws":24,"losses":170,"wins":84},"x-ai/grok-4.6":{"draws":31,"losses":77,"wins":42},"x-ai/grok-4.7":{"draws":2,"losses":21,"wins":5},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":20},"xiaomi/mimo-v2.5":{"draws":37,"losses":20,"wins":79},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":43,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":19,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":40,"losses":89,"wins":99},"z-ai/glm-5.3":{"draws":10,"losses":104,"wins":28},"z-ai/glm-5.3-flash":{"draws":30,"losses":64,"wins":58},"z-ai/glm-5.3-flashx":{"draws":1,"losses":31,"wins":12}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":52,"losses":43,"wins":39},"claude-fable-5":{"draws":28,"losses":53,"wins":11},"claude-fable-5-1":{"draws":7,"losses":62,"wins":1},"claude-opus-4-5":{"draws":25,"losses":66,"wins":11},"claude-opus-4-8":{"draws":4,"losses":8,"wins":0},"claude-opus-5":{"draws":10,"losses":52,"wins":0},"claude-opus-5-5":{"draws":3,"losses":37,"wins":0},"claude-sonnet-5":{"draws":54,"losses":74,"wins":20},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":63,"losses":45,"wins":40},"deepseek/deepseek-v4-pro":{"draws":44,"losses":44,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":30,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":19,"wins":8},"google/gemini-3.1-flash-lite":{"draws":6,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":43,"losses":54,"wins":25},"google/gemini-3.5-flash-lite":{"draws":91,"losses":84,"wins":75},"google/gemini-3.6-flash":{"draws":72,"losses":81,"wins":29},"google/gemini-3.8-flash":{"draws":27,"losses":57,"wins":8},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":6},"gpt-4.1":{"draws":2,"losses":4,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":12,"losses":10,"wins":4},"gpt-5.4":{"draws":58,"losses":41,"wins":15},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":6},"gpt-5.4-nano":{"draws":0,"losses":9,"wins":17},"gpt-5.5":{"draws":15,"losses":14,"wins":3},"gpt-5.6-luna":{"draws":68,"losses":43,"wins":29},"gpt-5.6-sol":{"draws":13,"losses":67,"wins":8},"gpt-5.6-terra":{"draws":45,"losses":72,"wins":13},"gpt-6-astra":{"draws":3,"losses":53,"wins":0},"gpt-6-luna":{"draws":9,"losses":9,"wins":6},"gpt-6-sol":{"draws":0,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":12,"losses":0,"wins":12},"inception/mercury-2.5-preview":{"draws":53,"losses":24,"wins":31},"inclusionai/ling-3.0-flash":{"draws":12,"losses":8,"wins":36},"meituan/longcat-2.0":{"draws":36,"losses":35,"wins":29},"meta/muse-glimmer-30b":{"draws":57,"losses":33,"wins":36},"meta/muse-spark-1.2":{"draws":27,"losses":44,"wins":9},"meta/muse-spark-1.3":{"draws":30,"losses":56,"wins":14},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":14},"mistralai/mistral-medium-3-5":{"draws":39,"losses":14,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":5},"moonshotai/kimi-k3":{"draws":39,"losses":61,"wins":16},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":10,"wins":15},"o3":{"draws":29,"losses":72,"wins":31},"openai/gpt-oss-120b":{"draws":38,"losses":21,"wins":21},"poolside/laguna-s-2.1":{"draws":39,"losses":25,"wins":20},"qwen/qwen3.7-max":{"draws":9,"losses":8,"wins":7},"qwen/qwen3.7-plus":{"draws":9,"losses":2,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":49,"wins":10},"qwen/qwen3.8-27b":{"draws":14,"losses":40,"wins":18},"qwen/qwen3.8-flash":{"draws":33,"losses":25,"wins":22},"qwen/qwen3.8-max":{"draws":52,"losses":56,"wins":10},"qwen/qwen3.8-max-0902":{"draws":10,"losses":24,"wins":4},"stealth/ox-alpha":{"draws":108,"losses":177,"wins":56},"stepfun/step-3.7-flash":{"draws":9,"losses":14,"wins":13},"tencent/hy3-preview":{"draws":12,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":34,"losses":34,"wins":18},"thinkingmachines/inkling":{"draws":38,"losses":31,"wins":27},"thinkingmachines/inkling-small":{"draws":63,"losses":35,"wins":48},"x-ai/grok-4.5":{"draws":33,"losses":40,"wins":9},"x-ai/grok-4.6":{"draws":31,"losses":42,"wins":13},"x-ai/grok-4.7":{"draws":0,"losses":14,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":31,"losses":16,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":10,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":4,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":7,"wins":2},"z-ai/glm-5.2":{"draws":73,"losses":63,"wins":32},"z-ai/glm-5.3":{"draws":32,"losses":40,"wins":6},"z-ai/glm-5.3-flash":{"draws":34,"losses":57,"wins":9},"z-ai/glm-5.3-flashx":{"draws":9,"losses":13,"wins":2}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":43,"losses":30,"wins":23},"claude-fable-5":{"draws":22,"losses":44,"wins":12},"claude-fable-5-1":{"draws":5,"losses":71,"wins":0},"claude-opus-4-5":{"draws":93,"losses":102,"wins":23},"claude-opus-4-8":{"draws":26,"losses":51,"wins":11},"claude-opus-5":{"draws":17,"losses":181,"wins":16},"claude-opus-5-5":{"draws":0,"losses":30,"wins":0},"claude-sonnet-5":{"draws":55,"losses":86,"wins":11},"cohere/north-mini-code":{"draws":39,"losses":24,"wins":3},"deepseek/deepseek-v4-flash":{"draws":70,"losses":43,"wins":35},"deepseek/deepseek-v4-pro":{"draws":34,"losses":36,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":42,"losses":34,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":14,"losses":19,"wins":31},"google/gemini-3.5-flash":{"draws":42,"losses":48,"wins":22},"google/gemini-3.5-flash-lite":{"draws":192,"losses":119,"wins":141},"google/gemini-3.6-flash":{"draws":167,"losses":158,"wins":61},"google/gemini-3.8-flash":{"draws":26,"losses":52,"wins":8},"google/gemma-4-31b-it":{"draws":6,"losses":23,"wins":25},"gpt-4.1":{"draws":12,"losses":14,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":6},"gpt-5":{"draws":28,"losses":24,"wins":30},"gpt-5.4":{"draws":62,"losses":57,"wins":11},"gpt-5.4-mini":{"draws":44,"losses":24,"wins":18},"gpt-5.4-nano":{"draws":48,"losses":34,"wins":48},"gpt-5.5":{"draws":44,"losses":32,"wins":22},"gpt-5.6-luna":{"draws":73,"losses":54,"wins":41},"gpt-5.6-sol":{"draws":33,"losses":134,"wins":3},"gpt-5.6-terra":{"draws":43,"losses":38,"wins":11},"gpt-6-astra":{"draws":16,"losses":56,"wins":0},"gpt-6-luna":{"draws":11,"losses":11,"wins":8},"gpt-6-sol":{"draws":7,"losses":19,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":2,"wins":4},"inception/mercury-2.5-preview":{"draws":28,"losses":17,"wins":23},"inclusionai/ling-3.0-flash":{"draws":82,"losses":20,"wins":48},"meituan/longcat-2.0":{"draws":94,"losses":74,"wins":68},"meta/muse-glimmer-30b":{"draws":50,"losses":19,"wins":25},"meta/muse-spark-1.2":{"draws":36,"losses":65,"wins":21},"meta/muse-spark-1.3":{"draws":26,"losses":37,"wins":15},"minimax/minimax-m3":{"draws":26,"losses":22,"wins":26},"mistralai/mistral-medium-3-5":{"draws":31,"losses":15,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":3,"wins":17},"moonshotai/kimi-k3":{"draws":90,"losses":95,"wins":23},"nex-agi/nex-n2-pro":{"draws":24,"losses":9,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":15,"wins":22},"o3":{"draws":59,"losses":86,"wins":59},"openai/gpt-oss-120b":{"draws":39,"losses":20,"wins":25},"poolside/laguna-s-2.1":{"draws":76,"losses":48,"wins":48},"qwen/qwen3.7-max":{"draws":26,"losses":25,"wins":19},"qwen/qwen3.7-plus":{"draws":32,"losses":6,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":39,"wins":8},"qwen/qwen3.8-27b":{"draws":14,"losses":32,"wins":18},"qwen/qwen3.8-flash":{"draws":32,"losses":22,"wins":12},"qwen/qwen3.8-max":{"draws":39,"losses":23,"wins":21},"qwen/qwen3.8-max-0902":{"draws":5,"losses":3,"wins":6},"stealth/ox-alpha":{"draws":98,"losses":140,"wins":45},"stepfun/step-3.7-flash":{"draws":24,"losses":34,"wins":20},"tencent/hy3-preview":{"draws":12,"losses":17,"wins":15},"tencent/hy4-preview":{"draws":41,"losses":38,"wins":15},"thinkingmachines/inkling":{"draws":85,"losses":58,"wins":85},"thinkingmachines/inkling-small":{"draws":59,"losses":20,"wins":38},"x-ai/grok-4.5":{"draws":67,"losses":123,"wins":38},"x-ai/grok-4.6":{"draws":31,"losses":36,"wins":11},"x-ai/grok-4.7":{"draws":0,"losses":9,"wins":3},"x-ai/grok-build-0.1":{"draws":23,"losses":17,"wins":10},"xiaomi/mimo-v2.5":{"draws":56,"losses":42,"wins":52},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":29,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":8,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":5,"wins":0},"z-ai/glm-5.2":{"draws":110,"losses":62,"wins":48},"z-ai/glm-5.3":{"draws":27,"losses":44,"wins":5},"z-ai/glm-5.3-flash":{"draws":42,"losses":46,"wins":14},"z-ai/glm-5.3-flashx":{"draws":6,"losses":9,"wins":5}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":12,"wins":13},"claude-fable-5":{"draws":4,"losses":13,"wins":3},"claude-fable-5-1":{"draws":1,"losses":23,"wins":0},"claude-opus-4-5":{"draws":51,"losses":59,"wins":26},"claude-opus-4-8":{"draws":28,"losses":39,"wins":21},"claude-opus-5":{"draws":17,"losses":107,"wins":18},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":3,"losses":20,"wins":5},"cohere/north-mini-code":{"draws":19,"losses":10,"wins":29},"deepseek/deepseek-v4-flash":{"draws":29,"losses":16,"wins":23},"deepseek/deepseek-v4-pro":{"draws":6,"losses":10,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":13,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":4,"wins":7},"google/gemini-3.1-flash-lite":{"draws":20,"losses":13,"wins":33},"google/gemini-3.5-flash":{"draws":19,"losses":13,"wins":16},"google/gemini-3.5-flash-lite":{"draws":25,"losses":27,"wins":14},"google/gemini-3.6-flash":{"draws":16,"losses":42,"wins":14},"google/gemini-3.8-flash":{"draws":4,"losses":15,"wins":11},"google/gemma-4-31b-it":{"draws":6,"losses":13,"wins":31},"gpt-4.1":{"draws":15,"losses":0,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":27,"losses":28,"wins":15},"gpt-5.4":{"draws":3,"losses":9,"wins":8},"gpt-5.4-mini":{"draws":26,"losses":13,"wins":27},"gpt-5.4-nano":{"draws":28,"losses":31,"wins":43},"gpt-5.5":{"draws":34,"losses":28,"wins":20},"gpt-5.6-luna":{"draws":3,"losses":6,"wins":5},"gpt-5.6-sol":{"draws":6,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":22,"wins":8},"gpt-6-astra":{"draws":4,"losses":21,"wins":1},"gpt-6-luna":{"draws":2,"losses":10,"wins":2},"gpt-6-sol":{"draws":3,"losses":9,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":35,"losses":7,"wins":28},"meituan/longcat-2.0":{"draws":27,"losses":6,"wins":34},"meta/muse-glimmer-30b":{"draws":9,"losses":6,"wins":11},"meta/muse-spark-1.2":{"draws":1,"losses":14,"wins":1},"meta/muse-spark-1.3":{"draws":6,"losses":10,"wins":8},"minimax/minimax-m3":{"draws":29,"losses":14,"wins":33},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":14,"losses":20,"wins":10},"nex-agi/nex-n2-pro":{"draws":17,"losses":6,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":15,"wins":24},"o3":{"draws":18,"losses":29,"wins":15},"openai/gpt-oss-120b":{"draws":9,"losses":7,"wins":8},"poolside/laguna-s-2.1":{"draws":26,"losses":19,"wins":25},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":10},"qwen/qwen3.7-plus":{"draws":26,"losses":12,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":10,"wins":4},"qwen/qwen3.8-27b":{"draws":0,"losses":22,"wins":6},"qwen/qwen3.8-flash":{"draws":14,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":11,"wins":5},"qwen/qwen3.8-max-0902":{"draws":6,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":15,"losses":46,"wins":21},"stepfun/step-3.7-flash":{"draws":18,"losses":8,"wins":22},"tencent/hy3-preview":{"draws":28,"losses":12,"wins":26},"tencent/hy4-preview":{"draws":9,"losses":11,"wins":4},"thinkingmachines/inkling":{"draws":31,"losses":13,"wins":38},"thinkingmachines/inkling-small":{"draws":7,"losses":10,"wins":11},"x-ai/grok-4.5":{"draws":20,"losses":24,"wins":14},"x-ai/grok-4.6":{"draws":3,"losses":7,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":11,"wins":2},"x-ai/grok-build-0.1":{"draws":22,"losses":16,"wins":12},"xiaomi/mimo-v2.5":{"draws":66,"losses":28,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":15,"wins":28},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":1},"z-ai/glm-5.2":{"draws":46,"losses":45,"wins":27},"z-ai/glm-5.3":{"draws":6,"losses":9,"wins":5},"z-ai/glm-5.3-flash":{"draws":6,"losses":10,"wins":4},"z-ai/glm-5.3-flashx":{"draws":5,"losses":9,"wins":4}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":7,"wins":2},"claude-fable-5":{"draws":4,"losses":11,"wins":1},"claude-fable-5-1":{"draws":3,"losses":5,"wins":0},"claude-opus-4-5":{"draws":46,"losses":33,"wins":19},"claude-opus-4-8":{"draws":15,"losses":43,"wins":16},"claude-opus-5":{"draws":14,"losses":44,"wins":10},"claude-opus-5-5":{"draws":1,"losses":7,"wins":0},"claude-sonnet-5":{"draws":8,"losses":12,"wins":4},"cohere/north-mini-code":{"draws":16,"losses":16,"wins":24},"deepseek/deepseek-v4-flash":{"draws":25,"losses":31,"wins":28},"deepseek/deepseek-v4-pro":{"draws":12,"losses":17,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":7,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":19,"losses":18,"wins":31},"google/gemini-3.5-flash":{"draws":13,"losses":12,"wins":3},"google/gemini-3.5-flash-lite":{"draws":25,"losses":17,"wins":12},"google/gemini-3.6-flash":{"draws":23,"losses":41,"wins":12},"google/gemini-3.8-flash":{"draws":6,"losses":16,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":24,"wins":14},"gpt-4.1":{"draws":10,"losses":6,"wins":4},"gpt-5":{"draws":14,"losses":15,"wins":9},"gpt-5.4":{"draws":3,"losses":19,"wins":4},"gpt-5.4-mini":{"draws":20,"losses":16,"wins":24},"gpt-5.4-nano":{"draws":22,"losses":41,"wins":43},"gpt-5.5":{"draws":37,"losses":33,"wins":10},"gpt-5.6-luna":{"draws":5,"losses":10,"wins":11},"gpt-5.6-sol":{"draws":4,"losses":17,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":7,"wins":3},"gpt-6-astra":{"draws":1,"losses":11,"wins":0},"gpt-6-luna":{"draws":3,"losses":7,"wins":4},"gpt-6-sol":{"draws":0,"losses":8,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":6,"wins":12},"inclusionai/ling-3.0-flash":{"draws":28,"losses":14,"wins":16},"meituan/longcat-2.0":{"draws":17,"losses":20,"wins":17},"meta/muse-glimmer-30b":{"draws":11,"losses":10,"wins":7},"meta/muse-spark-1.2":{"draws":2,"losses":18,"wins":6},"meta/muse-spark-1.3":{"draws":0,"losses":8,"wins":4},"minimax/minimax-m3":{"draws":13,"losses":21,"wins":20},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":15,"losses":19,"wins":2},"moonshotai/kimi-k3":{"draws":13,"losses":21,"wins":6},"nex-agi/nex-n2-pro":{"draws":18,"losses":15,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":20,"wins":20},"o3":{"draws":8,"losses":24,"wins":18},"openai/gpt-oss-120b":{"draws":9,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":32,"losses":22,"wins":6},"qwen/qwen3.7-max":{"draws":26,"losses":22,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":12,"wins":3},"qwen/qwen3.8-27b":{"draws":1,"losses":16,"wins":5},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":6},"qwen/qwen3.8-max":{"draws":7,"losses":5,"wins":10},"qwen/qwen3.8-max-0902":{"draws":4,"losses":3,"wins":1},"stealth/ox-alpha":{"draws":11,"losses":34,"wins":7},"stepfun/step-3.7-flash":{"draws":14,"losses":12,"wins":24},"tencent/hy3-preview":{"draws":24,"losses":18,"wins":12},"tencent/hy4-preview":{"draws":6,"losses":7,"wins":5},"thinkingmachines/inkling":{"draws":18,"losses":18,"wins":26},"thinkingmachines/inkling-small":{"draws":6,"losses":6,"wins":8},"x-ai/grok-4.5":{"draws":15,"losses":29,"wins":8},"x-ai/grok-4.6":{"draws":7,"losses":5,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":16,"wins":0},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":14},"xiaomi/mimo-v2.5":{"draws":59,"losses":34,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":24,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":47,"losses":47,"wins":18},"z-ai/glm-5.3":{"draws":1,"losses":17,"wins":1},"z-ai/glm-5.3-flash":{"draws":4,"losses":11,"wins":1},"z-ai/glm-5.3-flashx":{"draws":2,"losses":3,"wins":1}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":44,"losses":28,"wins":44},"claude-fable-5":{"draws":38,"losses":63,"wins":39},"claude-fable-5-1":{"draws":17,"losses":135,"wins":8},"claude-opus-4-5":{"draws":53,"losses":41,"wins":52},"claude-opus-4-8":{"draws":22,"losses":13,"wins":11},"claude-opus-5":{"draws":15,"losses":60,"wins":17},"claude-opus-5-5":{"draws":2,"losses":14,"wins":4},"claude-sonnet-5":{"draws":61,"losses":36,"wins":51},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":24},"deepseek/deepseek-v4-flash":{"draws":53,"losses":31,"wins":74},"deepseek/deepseek-v4-pro":{"draws":45,"losses":37,"wins":56},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":48,"wins":44},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":15,"wins":16},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":39,"losses":51,"wins":58},"google/gemini-3.5-flash-lite":{"draws":79,"losses":41,"wins":112},"google/gemini-3.6-flash":{"draws":66,"losses":102,"wins":78},"google/gemini-3.8-flash":{"draws":33,"losses":67,"wins":52},"google/gemma-4-31b-it":{"draws":5,"losses":0,"wins":17},"gpt-4.1":{"draws":4,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":12,"wins":16},"gpt-5.4":{"draws":34,"losses":50,"wins":62},"gpt-5.4-mini":{"draws":9,"losses":1,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":26},"gpt-5.5":{"draws":13,"losses":14,"wins":1},"gpt-5.6-luna":{"draws":57,"losses":28,"wins":47},"gpt-5.6-sol":{"draws":35,"losses":86,"wins":43},"gpt-5.6-terra":{"draws":54,"losses":30,"wins":58},"gpt-6-astra":{"draws":10,"losses":113,"wins":7},"gpt-6-luna":{"draws":6,"losses":5,"wins":13},"gpt-6-sol":{"draws":0,"losses":11,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":8},"inception/mercury-2.5-preview":{"draws":39,"losses":8,"wins":43},"inclusionai/ling-3.0-flash":{"draws":20,"losses":3,"wins":37},"meituan/longcat-2.0":{"draws":17,"losses":13,"wins":52},"meta/muse-glimmer-30b":{"draws":49,"losses":17,"wins":40},"meta/muse-spark-1.2":{"draws":28,"losses":29,"wins":47},"meta/muse-spark-1.3":{"draws":41,"losses":50,"wins":47},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":14},"mistralai/mistral-medium-3-5":{"draws":32,"losses":3,"wins":55},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":50,"losses":50,"wins":48},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":5,"wins":11},"o3":{"draws":16,"losses":46,"wins":80},"openai/gpt-oss-120b":{"draws":45,"losses":10,"wins":49},"poolside/laguna-s-2.1":{"draws":39,"losses":8,"wins":39},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":13,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":33,"wins":33},"qwen/qwen3.8-27b":{"draws":27,"losses":22,"wins":35},"qwen/qwen3.8-flash":{"draws":30,"losses":31,"wins":37},"qwen/qwen3.8-max":{"draws":54,"losses":43,"wins":53},"qwen/qwen3.8-max-0902":{"draws":11,"losses":12,"wins":9},"stealth/ox-alpha":{"draws":136,"losses":171,"wins":159},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":16},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":11},"tencent/hy4-preview":{"draws":42,"losses":56,"wins":42},"thinkingmachines/inkling":{"draws":42,"losses":12,"wins":34},"thinkingmachines/inkling-small":{"draws":48,"losses":17,"wins":79},"x-ai/grok-4.5":{"draws":29,"losses":50,"wins":33},"x-ai/grok-4.6":{"draws":45,"losses":58,"wins":45},"x-ai/grok-4.7":{"draws":2,"losses":13,"wins":7},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":28,"losses":8,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":4,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":9,"wins":4},"z-ai/glm-5.2":{"draws":67,"losses":52,"wins":67},"z-ai/glm-5.3":{"draws":37,"losses":76,"wins":29},"z-ai/glm-5.3-flash":{"draws":38,"losses":48,"wins":54},"z-ai/glm-5.3-flashx":{"draws":8,"losses":14,"wins":10}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":22,"wins":36},"claude-fable-5":{"draws":10,"losses":43,"wins":17},"claude-fable-5-1":{"draws":3,"losses":70,"wins":1},"claude-opus-4-5":{"draws":18,"losses":29,"wins":25},"claude-opus-4-8":{"draws":8,"losses":14,"wins":10},"claude-opus-5":{"draws":1,"losses":27,"wins":2},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":20,"losses":31,"wins":25},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":15},"deepseek/deepseek-v4-flash":{"draws":20,"losses":33,"wins":45},"deepseek/deepseek-v4-pro":{"draws":15,"losses":26,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":28,"losses":28,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":4,"wins":5},"google/gemini-3.1-flash-lite":{"draws":7,"losses":4,"wins":19},"google/gemini-3.5-flash":{"draws":21,"losses":24,"wins":41},"google/gemini-3.5-flash-lite":{"draws":29,"losses":33,"wins":78},"google/gemini-3.6-flash":{"draws":35,"losses":67,"wins":38},"google/gemini-3.8-flash":{"draws":19,"losses":51,"wins":30},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":6},"gpt-4.1":{"draws":0,"losses":4,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":2},"gpt-5":{"draws":3,"losses":12,"wins":13},"gpt-5.4":{"draws":21,"losses":38,"wins":15},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":21},"gpt-5.5":{"draws":3,"losses":13,"wins":6},"gpt-5.6-luna":{"draws":17,"losses":20,"wins":35},"gpt-5.6-sol":{"draws":13,"losses":46,"wins":23},"gpt-5.6-terra":{"draws":22,"losses":30,"wins":28},"gpt-6-astra":{"draws":0,"losses":78,"wins":2},"gpt-6-luna":{"draws":0,"losses":4,"wins":2},"gpt-6-sol":{"draws":1,"losses":7,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":13,"losses":6,"wins":35},"inclusionai/ling-3.0-flash":{"draws":10,"losses":6,"wins":22},"meituan/longcat-2.0":{"draws":15,"losses":13,"wins":32},"meta/muse-glimmer-30b":{"draws":24,"losses":9,"wins":39},"meta/muse-spark-1.2":{"draws":11,"losses":24,"wins":29},"meta/muse-spark-1.3":{"draws":13,"losses":34,"wins":25},"minimax/minimax-m3":{"draws":3,"losses":2,"wins":7},"mistralai/mistral-medium-3-5":{"draws":9,"losses":6,"wins":27},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":22,"losses":25,"wins":19},"nex-agi/nex-n2-pro":{"draws":2,"losses":7,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":7},"o3":{"draws":23,"losses":33,"wins":60},"openai/gpt-oss-120b":{"draws":14,"losses":18,"wins":40},"poolside/laguna-s-2.1":{"draws":14,"losses":18,"wins":32},"qwen/qwen3.7-max":{"draws":0,"losses":6,"wins":22},"qwen/qwen3.7-plus":{"draws":1,"losses":5,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":27,"losses":35,"wins":22},"qwen/qwen3.8-27b":{"draws":0,"losses":10,"wins":10},"qwen/qwen3.8-flash":{"draws":16,"losses":13,"wins":21},"qwen/qwen3.8-max":{"draws":20,"losses":29,"wins":27},"qwen/qwen3.8-max-0902":{"draws":0,"losses":4,"wins":6},"stealth/ox-alpha":{"draws":63,"losses":112,"wins":94},"stepfun/step-3.7-flash":{"draws":4,"losses":9,"wins":21},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":17},"tencent/hy4-preview":{"draws":20,"losses":34,"wins":16},"thinkingmachines/inkling":{"draws":20,"losses":11,"wins":39},"thinkingmachines/inkling-small":{"draws":20,"losses":12,"wins":54},"x-ai/grok-4.5":{"draws":7,"losses":32,"wins":33},"x-ai/grok-4.6":{"draws":20,"losses":29,"wins":27},"x-ai/grok-4.7":{"draws":0,"losses":8,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":8,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":2},"z-ai/glm-5.2":{"draws":35,"losses":38,"wins":45},"z-ai/glm-5.3":{"draws":11,"losses":42,"wins":13},"z-ai/glm-5.3-flash":{"draws":25,"losses":34,"wins":33},"z-ai/glm-5.3-flashx":{"draws":2,"losses":3,"wins":1}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":36,"losses":19,"wins":35},"claude-fable-5":{"draws":30,"losses":45,"wins":13},"claude-fable-5-1":{"draws":5,"losses":83,"wins":4},"claude-opus-4-5":{"draws":30,"losses":31,"wins":31},"claude-opus-4-8":{"draws":10,"losses":11,"wins":9},"claude-opus-5":{"draws":12,"losses":41,"wins":3},"claude-opus-5-5":{"draws":0,"losses":16,"wins":0},"claude-sonnet-5":{"draws":31,"losses":36,"wins":27},"cohere/north-mini-code":{"draws":11,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":41,"losses":20,"wins":43},"deepseek/deepseek-v4-pro":{"draws":27,"losses":30,"wins":31},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":25,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":8,"wins":8},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":6},"google/gemini-3.5-flash":{"draws":41,"losses":42,"wins":23},"google/gemini-3.5-flash-lite":{"draws":62,"losses":30,"wins":66},"google/gemini-3.6-flash":{"draws":66,"losses":59,"wins":39},"google/gemini-3.8-flash":{"draws":25,"losses":48,"wins":21},"google/gemma-4-31b-it":{"draws":10,"losses":5,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":8,"losses":12,"wins":4},"gpt-5.4":{"draws":22,"losses":28,"wins":26},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":7},"gpt-5.4-nano":{"draws":12,"losses":5,"wins":7},"gpt-5.5":{"draws":11,"losses":16,"wins":5},"gpt-5.6-luna":{"draws":38,"losses":27,"wins":33},"gpt-5.6-sol":{"draws":21,"losses":53,"wins":22},"gpt-5.6-terra":{"draws":25,"losses":29,"wins":30},"gpt-6-astra":{"draws":11,"losses":67,"wins":2},"gpt-6-luna":{"draws":0,"losses":5,"wins":7},"gpt-6-sol":{"draws":2,"losses":7,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":35,"losses":7,"wins":32},"inclusionai/ling-3.0-flash":{"draws":18,"losses":9,"wins":27},"meituan/longcat-2.0":{"draws":30,"losses":10,"wins":24},"meta/muse-glimmer-30b":{"draws":38,"losses":22,"wins":16},"meta/muse-spark-1.2":{"draws":23,"losses":22,"wins":25},"meta/muse-spark-1.3":{"draws":27,"losses":43,"wins":22},"minimax/minimax-m3":{"draws":11,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":24,"losses":8,"wins":26},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":36,"losses":27,"wins":19},"nex-agi/nex-n2-pro":{"draws":16,"losses":2,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":9,"wins":13},"o3":{"draws":28,"losses":41,"wins":35},"openai/gpt-oss-120b":{"draws":33,"losses":22,"wins":25},"poolside/laguna-s-2.1":{"draws":32,"losses":12,"wins":22},"qwen/qwen3.7-max":{"draws":14,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":13,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":37,"wins":31},"qwen/qwen3.8-27b":{"draws":16,"losses":21,"wins":13},"qwen/qwen3.8-flash":{"draws":14,"losses":5,"wins":5},"qwen/qwen3.8-max":{"draws":35,"losses":23,"wins":30},"qwen/qwen3.8-max-0902":{"draws":7,"losses":5,"wins":10},"stealth/ox-alpha":{"draws":88,"losses":108,"wins":87},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":9},"tencent/hy3-preview":{"draws":15,"losses":6,"wins":5},"tencent/hy4-preview":{"draws":25,"losses":37,"wins":28},"thinkingmachines/inkling":{"draws":30,"losses":16,"wins":26},"thinkingmachines/inkling-small":{"draws":46,"losses":19,"wins":33},"x-ai/grok-4.5":{"draws":16,"losses":31,"wins":13},"x-ai/grok-4.6":{"draws":35,"losses":35,"wins":18},"x-ai/grok-4.7":{"draws":0,"losses":9,"wins":1},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":14,"losses":3,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":9,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":5,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":49,"losses":25,"wins":44},"z-ai/glm-5.3":{"draws":24,"losses":56,"wins":14},"z-ai/glm-5.3-flash":{"draws":29,"losses":26,"wins":31},"z-ai/glm-5.3-flashx":{"draws":6,"losses":13,"wins":7}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":49,"losses":44,"wins":47},"claude-fable-5":{"draws":21,"losses":72,"wins":41},"claude-fable-5-1":{"draws":6,"losses":139,"wins":5},"claude-opus-4-5":{"draws":45,"losses":39,"wins":71},"claude-opus-4-8":{"draws":14,"losses":22,"wins":18},"claude-opus-5":{"draws":12,"losses":54,"wins":10},"claude-opus-5-5":{"draws":5,"losses":33,"wins":0},"claude-sonnet-5":{"draws":40,"losses":46,"wins":61},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":16},"deepseek/deepseek-v4-flash":{"draws":61,"losses":28,"wins":65},"deepseek/deepseek-v4-pro":{"draws":36,"losses":37,"wins":53},"deepseek/deepseek-v4-pro-0813":{"draws":46,"losses":39,"wins":41},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":15,"wins":10},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":49,"losses":53,"wins":34},"google/gemini-3.5-flash-lite":{"draws":83,"losses":55,"wins":87},"google/gemini-3.6-flash":{"draws":70,"losses":95,"wins":88},"google/gemini-3.8-flash":{"draws":40,"losses":56,"wins":44},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":3},"gpt-4.1":{"draws":8,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":8,"losses":5,"wins":13},"gpt-5.4":{"draws":45,"losses":50,"wins":51},"gpt-5.4-mini":{"draws":12,"losses":9,"wins":11},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":20},"gpt-5.5":{"draws":11,"losses":16,"wins":19},"gpt-5.6-luna":{"draws":55,"losses":27,"wins":62},"gpt-5.6-sol":{"draws":33,"losses":80,"wins":32},"gpt-5.6-terra":{"draws":63,"losses":35,"wins":44},"gpt-6-astra":{"draws":18,"losses":112,"wins":4},"gpt-6-luna":{"draws":9,"losses":5,"wins":14},"gpt-6-sol":{"draws":4,"losses":11,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":1,"wins":5},"inception/mercury-2.5-preview":{"draws":48,"losses":11,"wins":37},"inclusionai/ling-3.0-flash":{"draws":27,"losses":9,"wins":29},"meituan/longcat-2.0":{"draws":36,"losses":18,"wins":42},"meta/muse-glimmer-30b":{"draws":36,"losses":32,"wins":46},"meta/muse-spark-1.2":{"draws":29,"losses":36,"wins":38},"meta/muse-spark-1.3":{"draws":27,"losses":62,"wins":25},"minimax/minimax-m3":{"draws":9,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":29,"losses":10,"wins":41},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":6},"moonshotai/kimi-k3":{"draws":37,"losses":43,"wins":41},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":6,"wins":19},"o3":{"draws":28,"losses":48,"wins":84},"openai/gpt-oss-120b":{"draws":52,"losses":10,"wins":56},"poolside/laguna-s-2.1":{"draws":39,"losses":21,"wins":23},"qwen/qwen3.7-max":{"draws":16,"losses":5,"wins":11},"qwen/qwen3.7-plus":{"draws":7,"losses":10,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":54,"losses":53,"wins":43},"qwen/qwen3.8-27b":{"draws":20,"losses":27,"wins":29},"qwen/qwen3.8-flash":{"draws":35,"losses":30,"wins":23},"qwen/qwen3.8-max":{"draws":54,"losses":59,"wins":59},"qwen/qwen3.8-max-0902":{"draws":6,"losses":12,"wins":6},"stealth/ox-alpha":{"draws":133,"losses":192,"wins":163},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":25},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":7},"tencent/hy4-preview":{"draws":31,"losses":62,"wins":45},"thinkingmachines/inkling":{"draws":38,"losses":23,"wins":43},"thinkingmachines/inkling-small":{"draws":100,"losses":68,"wins":113},"x-ai/grok-4.5":{"draws":35,"losses":48,"wins":38},"x-ai/grok-4.6":{"draws":41,"losses":66,"wins":47},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":35,"losses":7,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":4,"wins":9},"z-ai/glm-5.2":{"draws":64,"losses":45,"wins":53},"z-ai/glm-5.3":{"draws":32,"losses":68,"wins":28},"z-ai/glm-5.3-flash":{"draws":42,"losses":47,"wins":53},"z-ai/glm-5.3-flashx":{"draws":14,"losses":6,"wins":6}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":3,"wins":12},"claude-fable-5":{"draws":8,"losses":14,"wins":4},"claude-fable-5-1":{"draws":2,"losses":25,"wins":5},"claude-opus-4-5":{"draws":7,"losses":7,"wins":16},"claude-opus-4-8":{"draws":10,"losses":3,"wins":11},"claude-opus-5":{"draws":9,"losses":21,"wins":12},"claude-opus-5-5":{"draws":3,"losses":31,"wins":2},"claude-sonnet-5":{"draws":10,"losses":2,"wins":8},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":12},"deepseek/deepseek-v4-flash":{"draws":6,"losses":4,"wins":30},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":5,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":21,"wins":20},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":25},"google/gemini-3.5-flash":{"draws":8,"losses":7,"wins":7},"google/gemini-3.5-flash-lite":{"draws":12,"losses":5,"wins":21},"google/gemini-3.6-flash":{"draws":15,"losses":18,"wins":11},"google/gemini-3.8-flash":{"draws":6,"losses":7,"wins":3},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":10},"gpt-4.1":{"draws":6,"losses":0,"wins":10},"gpt-5":{"draws":8,"losses":5,"wins":7},"gpt-5.4":{"draws":9,"losses":21,"wins":10},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":6},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":14},"gpt-5.5":{"draws":13,"losses":8,"wins":11},"gpt-5.6-luna":{"draws":12,"losses":2,"wins":18},"gpt-5.6-sol":{"draws":5,"losses":11,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":1,"wins":10},"gpt-6-astra":{"draws":3,"losses":21,"wins":2},"gpt-6-luna":{"draws":23,"losses":15,"wins":10},"gpt-6-sol":{"draws":10,"losses":29,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":11},"inclusionai/ling-3.0-flash":{"draws":11,"losses":1,"wins":20},"meituan/longcat-2.0":{"draws":12,"losses":7,"wins":30},"meta/muse-glimmer-30b":{"draws":17,"losses":0,"wins":13},"meta/muse-spark-1.2":{"draws":8,"losses":6,"wins":14},"meta/muse-spark-1.3":{"draws":13,"losses":9,"wins":6},"minimax/minimax-m3":{"draws":6,"losses":5,"wins":3},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":10,"losses":4,"wins":14},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":16},"o3":{"draws":5,"losses":7,"wins":16},"openai/gpt-oss-120b":{"draws":10,"losses":4,"wins":24},"poolside/laguna-s-2.1":{"draws":5,"losses":6,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":9,"wins":12},"qwen/qwen3.8-27b":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":10,"wins":5},"qwen/qwen3.8-max":{"draws":6,"losses":6,"wins":12},"qwen/qwen3.8-max-0902":{"draws":16,"losses":30,"wins":30},"stealth/ox-alpha":{"draws":23,"losses":36,"wins":37},"stepfun/step-3.7-flash":{"draws":3,"losses":2,"wins":11},"tencent/hy3-preview":{"draws":4,"losses":5,"wins":7},"tencent/hy4-preview":{"draws":7,"losses":11,"wins":12},"thinkingmachines/inkling":{"draws":11,"losses":0,"wins":11},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":8},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":7},"x-ai/grok-4.6":{"draws":9,"losses":13,"wins":8},"x-ai/grok-4.7":{"draws":7,"losses":19,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":24,"losses":4,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":5,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":13,"losses":30,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":13},"z-ai/glm-5.2":{"draws":15,"losses":6,"wins":25},"z-ai/glm-5.3":{"draws":11,"losses":17,"wins":4},"z-ai/glm-5.3-flash":{"draws":1,"losses":8,"wins":9},"z-ai/glm-5.3-flashx":{"draws":20,"losses":30,"wins":36}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":99,"losses":87,"wins":194},"claude-fable-5":{"draws":103,"losses":267,"wins":104},"claude-fable-5-1":{"draws":52,"losses":475,"wins":27},"claude-opus-4-5":{"draws":135,"losses":131,"wins":195},"claude-opus-4-8":{"draws":36,"losses":37,"wins":61},"claude-opus-5":{"draws":37,"losses":207,"wins":37},"claude-opus-5-5":{"draws":11,"losses":88,"wins":5},"claude-sonnet-5":{"draws":121,"losses":142,"wins":206},"cohere/north-mini-code":{"draws":10,"losses":11,"wins":39},"deepseek/deepseek-v4-flash":{"draws":153,"losses":104,"wins":208},"deepseek/deepseek-v4-pro":{"draws":133,"losses":139,"wins":156},"deepseek/deepseek-v4-pro-0813":{"draws":131,"losses":142,"wins":169},"deepseek/deepseek-v4.1-flash":{"draws":23,"losses":35,"wins":48},"google/gemini-3.1-flash-lite":{"draws":17,"losses":9,"wins":38},"google/gemini-3.5-flash":{"draws":118,"losses":179,"wins":194},"google/gemini-3.5-flash-lite":{"draws":204,"losses":168,"wins":387},"google/gemini-3.6-flash":{"draws":177,"losses":297,"wins":287},"google/gemini-3.8-flash":{"draws":115,"losses":216,"wins":157},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":40},"gpt-4.1":{"draws":15,"losses":8,"wins":23},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":16},"gpt-5":{"draws":36,"losses":32,"wins":56},"gpt-5.4":{"draws":148,"losses":176,"wins":135},"gpt-5.4-mini":{"draws":24,"losses":26,"wins":44},"gpt-5.4-nano":{"draws":21,"losses":20,"wins":77},"gpt-5.5":{"draws":33,"losses":26,"wins":43},"gpt-5.6-luna":{"draws":145,"losses":99,"wins":161},"gpt-5.6-sol":{"draws":72,"losses":282,"wins":141},"gpt-5.6-terra":{"draws":148,"losses":121,"wins":163},"gpt-6-astra":{"draws":67,"losses":392,"wins":33},"gpt-6-luna":{"draws":18,"losses":18,"wins":22},"gpt-6-sol":{"draws":13,"losses":51,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":33,"losses":3,"wins":26},"inception/mercury-2.5-preview":{"draws":99,"losses":38,"wins":136},"inclusionai/ling-3.0-flash":{"draws":36,"losses":24,"wins":70},"meituan/longcat-2.0":{"draws":69,"losses":44,"wins":173},"meta/muse-glimmer-30b":{"draws":119,"losses":57,"wins":198},"meta/muse-spark-1.2":{"draws":90,"losses":106,"wins":187},"meta/muse-spark-1.3":{"draws":103,"losses":160,"wins":160},"minimax/minimax-m3":{"draws":28,"losses":10,"wins":40},"mistralai/mistral-medium-3-5":{"draws":74,"losses":44,"wins":122},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":11,"wins":10},"moonshotai/kimi-k3":{"draws":115,"losses":140,"wins":176},"nex-agi/nex-n2-pro":{"draws":17,"losses":11,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":9,"wins":57},"o3":{"draws":54,"losses":181,"wins":209},"openai/gpt-oss-120b":{"draws":108,"losses":56,"wins":177},"poolside/laguna-s-2.1":{"draws":98,"losses":45,"wins":140},"qwen/qwen3.7-max":{"draws":15,"losses":21,"wins":46},"qwen/qwen3.7-plus":{"draws":11,"losses":7,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":136,"losses":159,"wins":171},"qwen/qwen3.8-27b":{"draws":63,"losses":94,"wins":112},"qwen/qwen3.8-flash":{"draws":88,"losses":87,"wins":108},"qwen/qwen3.8-max":{"draws":133,"losses":163,"wins":192},"qwen/qwen3.8-max-0902":{"draws":23,"losses":37,"wins":36},"stealth/ox-alpha":{"draws":388,"losses":683,"wins":683},"stepfun/step-3.7-flash":{"draws":18,"losses":25,"wins":67},"tencent/hy3-preview":{"draws":35,"losses":10,"wins":23},"tencent/hy4-preview":{"draws":112,"losses":209,"wins":148},"thinkingmachines/inkling":{"draws":84,"losses":60,"wins":197},"thinkingmachines/inkling-small":{"draws":164,"losses":70,"wins":226},"x-ai/grok-4.5":{"draws":79,"losses":150,"wins":105},"x-ai/grok-4.6":{"draws":143,"losses":197,"wins":162},"x-ai/grok-4.7":{"draws":7,"losses":27,"wins":8},"x-ai/grok-build-0.1":{"draws":14,"losses":6,"wins":26},"xiaomi/mimo-v2.5":{"draws":53,"losses":30,"wins":107},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":31,"wins":49},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":27,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":19,"wins":14},"z-ai/glm-5.2":{"draws":167,"losses":141,"wins":262},"z-ai/glm-5.3":{"draws":89,"losses":241,"wins":116},"z-ai/glm-5.3-flash":{"draws":118,"losses":190,"wins":179},"z-ai/glm-5.3-flashx":{"draws":15,"losses":46,"wins":41}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":20,"wins":14},"claude-fable-5":{"draws":0,"losses":33,"wins":3},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-opus-4-5":{"draws":38,"losses":82,"wins":24},"claude-opus-4-8":{"draws":16,"losses":42,"wins":14},"claude-opus-5":{"draws":11,"losses":74,"wins":1},"claude-opus-5-5":{"draws":2,"losses":24,"wins":0},"claude-sonnet-5":{"draws":9,"losses":32,"wins":21},"cohere/north-mini-code":{"draws":14,"losses":6,"wins":18},"deepseek/deepseek-v4-flash":{"draws":23,"losses":22,"wins":31},"deepseek/deepseek-v4-pro":{"draws":12,"losses":26,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":16,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":11,"wins":4},"google/gemini-3.1-flash-lite":{"draws":12,"losses":7,"wins":37},"google/gemini-3.5-flash":{"draws":13,"losses":28,"wins":13},"google/gemini-3.5-flash-lite":{"draws":44,"losses":58,"wins":70},"google/gemini-3.6-flash":{"draws":27,"losses":103,"wins":21},"google/gemini-3.8-flash":{"draws":11,"losses":24,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":26},"gpt-4.1":{"draws":8,"losses":11,"wins":5},"gpt-5":{"draws":24,"losses":31,"wins":5},"gpt-5.4":{"draws":13,"losses":40,"wins":9},"gpt-5.4-mini":{"draws":20,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":28,"losses":46,"wins":20},"gpt-5.5":{"draws":10,"losses":45,"wins":11},"gpt-5.6-luna":{"draws":20,"losses":21,"wins":27},"gpt-5.6-sol":{"draws":2,"losses":38,"wins":12},"gpt-5.6-terra":{"draws":11,"losses":18,"wins":9},"gpt-6-astra":{"draws":0,"losses":26,"wins":0},"gpt-6-luna":{"draws":4,"losses":7,"wins":5},"gpt-6-sol":{"draws":2,"losses":17,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":11,"losses":6,"wins":21},"inclusionai/ling-3.0-flash":{"draws":20,"losses":10,"wins":26},"meituan/longcat-2.0":{"draws":23,"losses":40,"wins":47},"meta/muse-glimmer-30b":{"draws":14,"losses":17,"wins":7},"meta/muse-spark-1.2":{"draws":2,"losses":33,"wins":11},"meta/muse-spark-1.3":{"draws":8,"losses":36,"wins":8},"minimax/minimax-m3":{"draws":13,"losses":17,"wins":10},"mistralai/mistral-medium-3-5":{"draws":8,"losses":7,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":8,"wins":5},"moonshotai/kimi-k3":{"draws":20,"losses":49,"wins":11},"nex-agi/nex-n2-pro":{"draws":15,"losses":18,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":34,"losses":24,"wins":20},"o3":{"draws":37,"losses":104,"wins":51},"openai/gpt-oss-120b":{"draws":9,"losses":13,"wins":14},"poolside/laguna-s-2.1":{"draws":24,"losses":20,"wins":34},"qwen/qwen3.7-max":{"draws":18,"losses":22,"wins":8},"qwen/qwen3.7-plus":{"draws":14,"losses":24,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":16,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":21,"wins":9},"qwen/qwen3.8-flash":{"draws":9,"losses":9,"wins":6},"qwen/qwen3.8-max":{"draws":6,"losses":25,"wins":3},"qwen/qwen3.8-max-0902":{"draws":3,"losses":11,"wins":2},"stealth/ox-alpha":{"draws":18,"losses":67,"wins":25},"stepfun/step-3.7-flash":{"draws":0,"losses":10,"wins":10},"tencent/hy3-preview":{"draws":12,"losses":9,"wins":13},"tencent/hy4-preview":{"draws":6,"losses":15,"wins":7},"thinkingmachines/inkling":{"draws":23,"losses":35,"wins":50},"thinkingmachines/inkling-small":{"draws":15,"losses":16,"wins":13},"x-ai/grok-4.5":{"draws":13,"losses":54,"wins":15},"x-ai/grok-4.6":{"draws":7,"losses":18,"wins":7},"x-ai/grok-4.7":{"draws":1,"losses":11,"wins":0},"x-ai/grok-build-0.1":{"draws":16,"losses":13,"wins":3},"xiaomi/mimo-v2.5":{"draws":54,"losses":43,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":23,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":26,"losses":47,"wins":23},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":2},"z-ai/glm-5.3-flash":{"draws":17,"losses":19,"wins":6},"z-ai/glm-5.3-flashx":{"draws":4,"losses":5,"wins":1}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":9,"wins":9},"claude-fable-5":{"draws":2,"losses":14,"wins":2},"claude-fable-5-1":{"draws":2,"losses":28,"wins":2},"claude-opus-4-5":{"draws":37,"losses":40,"wins":17},"claude-opus-4-8":{"draws":25,"losses":31,"wins":14},"claude-opus-5":{"draws":22,"losses":95,"wins":11},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":15,"losses":16,"wins":9},"cohere/north-mini-code":{"draws":10,"losses":7,"wins":19},"deepseek/deepseek-v4-flash":{"draws":24,"losses":21,"wins":27},"deepseek/deepseek-v4-pro":{"draws":13,"losses":5,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":9,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":20,"losses":16,"wins":18},"google/gemini-3.5-flash":{"draws":8,"losses":9,"wins":9},"google/gemini-3.5-flash-lite":{"draws":33,"losses":9,"wins":22},"google/gemini-3.6-flash":{"draws":25,"losses":32,"wins":21},"google/gemini-3.8-flash":{"draws":14,"losses":15,"wins":3},"google/gemma-4-31b-it":{"draws":18,"losses":7,"wins":19},"gpt-4.1":{"draws":20,"losses":12,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":33,"losses":31,"wins":24},"gpt-5.4":{"draws":14,"losses":9,"wins":9},"gpt-5.4-mini":{"draws":18,"losses":11,"wins":13},"gpt-5.4-nano":{"draws":16,"losses":11,"wins":29},"gpt-5.5":{"draws":37,"losses":32,"wins":13},"gpt-5.6-luna":{"draws":2,"losses":10,"wins":6},"gpt-5.6-sol":{"draws":5,"losses":12,"wins":3},"gpt-5.6-terra":{"draws":10,"losses":10,"wins":4},"gpt-6-astra":{"draws":1,"losses":11,"wins":0},"gpt-6-luna":{"draws":10,"losses":9,"wins":5},"gpt-6-sol":{"draws":4,"losses":18,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":13,"losses":8,"wins":5},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":22},"meituan/longcat-2.0":{"draws":28,"losses":23,"wins":23},"meta/muse-glimmer-30b":{"draws":7,"losses":3,"wins":10},"meta/muse-spark-1.2":{"draws":7,"losses":15,"wins":8},"meta/muse-spark-1.3":{"draws":2,"losses":20,"wins":4},"minimax/minimax-m3":{"draws":25,"losses":12,"wins":27},"mistralai/mistral-medium-3-5":{"draws":8,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":6,"wins":7},"moonshotai/kimi-k3":{"draws":15,"losses":14,"wins":3},"nex-agi/nex-n2-pro":{"draws":26,"losses":9,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":49,"losses":14,"wins":25},"o3":{"draws":24,"losses":25,"wins":21},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":6},"poolside/laguna-s-2.1":{"draws":12,"losses":15,"wins":17},"qwen/qwen3.7-max":{"draws":28,"losses":26,"wins":12},"qwen/qwen3.7-plus":{"draws":24,"losses":12,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":11,"wins":7},"qwen/qwen3.8-27b":{"draws":10,"losses":17,"wins":5},"qwen/qwen3.8-flash":{"draws":15,"losses":5,"wins":6},"qwen/qwen3.8-max":{"draws":6,"losses":7,"wins":5},"qwen/qwen3.8-max-0902":{"draws":4,"losses":7,"wins":5},"stealth/ox-alpha":{"draws":35,"losses":23,"wins":10},"stepfun/step-3.7-flash":{"draws":12,"losses":13,"wins":9},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":9,"losses":12,"wins":7},"thinkingmachines/inkling":{"draws":25,"losses":22,"wins":19},"thinkingmachines/inkling-small":{"draws":20,"losses":5,"wins":13},"x-ai/grok-4.5":{"draws":13,"losses":33,"wins":8},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":9,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":9},"xiaomi/mimo-v2.5":{"draws":52,"losses":31,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":16,"losses":15,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":43,"losses":33,"wins":26},"z-ai/glm-5.3":{"draws":1,"losses":12,"wins":3},"z-ai/glm-5.3-flash":{"draws":7,"losses":15,"wins":2},"z-ai/glm-5.3-flashx":{"draws":3,"losses":4,"wins":5}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":47,"losses":21,"wins":68},"claude-fable-5":{"draws":25,"losses":83,"wins":30},"claude-fable-5-1":{"draws":6,"losses":128,"wins":14},"claude-opus-4-5":{"draws":39,"losses":41,"wins":62},"claude-opus-4-8":{"draws":14,"losses":19,"wins":27},"claude-opus-5":{"draws":9,"losses":63,"wins":10},"claude-opus-5-5":{"draws":0,"losses":15,"wins":3},"claude-sonnet-5":{"draws":48,"losses":35,"wins":59},"cohere/north-mini-code":{"draws":10,"losses":1,"wins":9},"deepseek/deepseek-v4-flash":{"draws":40,"losses":27,"wins":67},"deepseek/deepseek-v4-pro":{"draws":40,"losses":40,"wins":58},"deepseek/deepseek-v4-pro-0813":{"draws":32,"losses":38,"wins":50},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":12,"wins":10},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":18},"google/gemini-3.5-flash":{"draws":33,"losses":48,"wins":77},"google/gemini-3.5-flash-lite":{"draws":80,"losses":46,"wins":110},"google/gemini-3.6-flash":{"draws":56,"losses":105,"wins":97},"google/gemini-3.8-flash":{"draws":26,"losses":43,"wins":49},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":11},"gpt-4.1":{"draws":0,"losses":5,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":17,"losses":9,"wins":12},"gpt-5.4":{"draws":30,"losses":49,"wins":47},"gpt-5.4-mini":{"draws":15,"losses":8,"wins":15},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":23},"gpt-5.5":{"draws":15,"losses":10,"wins":11},"gpt-5.6-luna":{"draws":42,"losses":23,"wins":65},"gpt-5.6-sol":{"draws":24,"losses":77,"wins":49},"gpt-5.6-terra":{"draws":36,"losses":36,"wins":50},"gpt-6-astra":{"draws":11,"losses":107,"wins":12},"gpt-6-luna":{"draws":2,"losses":5,"wins":9},"gpt-6-sol":{"draws":2,"losses":11,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":9},"inception/mercury-2.5-preview":{"draws":40,"losses":8,"wins":44},"inclusionai/ling-3.0-flash":{"draws":11,"losses":6,"wins":27},"meituan/longcat-2.0":{"draws":22,"losses":13,"wins":47},"meta/muse-glimmer-30b":{"draws":44,"losses":13,"wins":49},"meta/muse-spark-1.2":{"draws":22,"losses":33,"wins":49},"meta/muse-spark-1.3":{"draws":26,"losses":40,"wins":52},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":14},"mistralai/mistral-medium-3-5":{"draws":31,"losses":6,"wins":39},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":41,"losses":48,"wins":35},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":3,"wins":19},"o3":{"draws":24,"losses":52,"wins":74},"openai/gpt-oss-120b":{"draws":34,"losses":18,"wins":34},"poolside/laguna-s-2.1":{"draws":41,"losses":15,"wins":38},"qwen/qwen3.7-max":{"draws":9,"losses":4,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":42,"wins":56},"qwen/qwen3.8-27b":{"draws":20,"losses":16,"wins":34},"qwen/qwen3.8-flash":{"draws":25,"losses":28,"wins":37},"qwen/qwen3.8-max":{"draws":31,"losses":45,"wins":62},"qwen/qwen3.8-max-0902":{"draws":7,"losses":12,"wins":11},"stealth/ox-alpha":{"draws":112,"losses":148,"wins":209},"stepfun/step-3.7-flash":{"draws":6,"losses":7,"wins":15},"tencent/hy3-preview":{"draws":9,"losses":7,"wins":12},"tencent/hy4-preview":{"draws":14,"losses":25,"wins":25},"thinkingmachines/inkling":{"draws":45,"losses":15,"wins":52},"thinkingmachines/inkling-small":{"draws":48,"losses":17,"wins":69},"x-ai/grok-4.5":{"draws":27,"losses":37,"wins":44},"x-ai/grok-4.6":{"draws":42,"losses":57,"wins":41},"x-ai/grok-4.7":{"draws":0,"losses":10,"wins":8},"x-ai/grok-build-0.1":{"draws":8,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":47},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":6,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":8,"wins":4},"z-ai/glm-5.2":{"draws":52,"losses":35,"wins":77},"z-ai/glm-5.3":{"draws":21,"losses":89,"wins":26},"z-ai/glm-5.3-flash":{"draws":31,"losses":51,"wins":38},"z-ai/glm-5.3-flashx":{"draws":1,"losses":6,"wins":11}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":57,"wins":35},"claude-fable-5":{"draws":18,"losses":58,"wins":2},"claude-fable-5-1":{"draws":7,"losses":75,"wins":0},"claude-opus-4-5":{"draws":95,"losses":143,"wins":44},"claude-opus-4-8":{"draws":24,"losses":67,"wins":17},"claude-opus-5":{"draws":15,"losses":148,"wins":21},"claude-opus-5-5":{"draws":0,"losses":32,"wins":0},"claude-sonnet-5":{"draws":64,"losses":110,"wins":26},"cohere/north-mini-code":{"draws":16,"losses":25,"wins":23},"deepseek/deepseek-v4-flash":{"draws":57,"losses":56,"wins":53},"deepseek/deepseek-v4-pro":{"draws":35,"losses":46,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":35,"losses":39,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":10,"wins":1},"google/gemini-3.1-flash-lite":{"draws":30,"losses":29,"wins":47},"google/gemini-3.5-flash":{"draws":37,"losses":49,"wins":32},"google/gemini-3.5-flash-lite":{"draws":183,"losses":196,"wins":127},"google/gemini-3.6-flash":{"draws":168,"losses":238,"wins":72},"google/gemini-3.8-flash":{"draws":31,"losses":49,"wins":8},"google/gemma-4-31b-it":{"draws":12,"losses":15,"wins":21},"gpt-4.1":{"draws":12,"losses":13,"wins":19},"gpt-4.1-nano":{"draws":0,"losses":12,"wins":0},"gpt-5":{"draws":30,"losses":42,"wins":24},"gpt-5.4":{"draws":41,"losses":82,"wins":29},"gpt-5.4-mini":{"draws":29,"losses":20,"wins":21},"gpt-5.4-nano":{"draws":17,"losses":48,"wins":27},"gpt-5.5":{"draws":32,"losses":57,"wins":23},"gpt-5.6-luna":{"draws":74,"losses":93,"wins":43},"gpt-5.6-sol":{"draws":27,"losses":125,"wins":12},"gpt-5.6-terra":{"draws":30,"losses":53,"wins":17},"gpt-6-astra":{"draws":6,"losses":72,"wins":0},"gpt-6-luna":{"draws":12,"losses":9,"wins":3},"gpt-6-sol":{"draws":3,"losses":28,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":48,"losses":11,"wins":23},"inclusionai/ling-3.0-flash":{"draws":61,"losses":47,"wins":52},"meituan/longcat-2.0":{"draws":54,"losses":68,"wins":92},"meta/muse-glimmer-30b":{"draws":48,"losses":34,"wins":28},"meta/muse-spark-1.2":{"draws":47,"losses":72,"wins":21},"meta/muse-spark-1.3":{"draws":25,"losses":35,"wins":10},"minimax/minimax-m3":{"draws":18,"losses":28,"wins":32},"mistralai/mistral-medium-3-5":{"draws":26,"losses":13,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":15,"wins":13},"moonshotai/kimi-k3":{"draws":94,"losses":111,"wins":27},"nex-agi/nex-n2-pro":{"draws":16,"losses":22,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":50,"losses":41,"wins":35},"o3":{"draws":61,"losses":163,"wins":67},"openai/gpt-oss-120b":{"draws":38,"losses":27,"wins":31},"poolside/laguna-s-2.1":{"draws":85,"losses":85,"wins":58},"qwen/qwen3.7-max":{"draws":31,"losses":38,"wins":13},"qwen/qwen3.7-plus":{"draws":18,"losses":26,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":42,"losses":34,"wins":12},"qwen/qwen3.8-27b":{"draws":20,"losses":39,"wins":11},"qwen/qwen3.8-flash":{"draws":30,"losses":26,"wins":16},"qwen/qwen3.8-max":{"draws":38,"losses":43,"wins":23},"qwen/qwen3.8-max-0902":{"draws":11,"losses":11,"wins":0},"stealth/ox-alpha":{"draws":84,"losses":197,"wins":60},"stepfun/step-3.7-flash":{"draws":23,"losses":50,"wins":35},"tencent/hy3-preview":{"draws":25,"losses":19,"wins":22},"tencent/hy4-preview":{"draws":45,"losses":52,"wins":15},"thinkingmachines/inkling":{"draws":40,"losses":52,"wins":52},"thinkingmachines/inkling-small":{"draws":41,"losses":21,"wins":38},"x-ai/grok-4.5":{"draws":71,"losses":113,"wins":32},"x-ai/grok-4.6":{"draws":27,"losses":35,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":8,"wins":1},"x-ai/grok-build-0.1":{"draws":18,"losses":11,"wins":11},"xiaomi/mimo-v2.5":{"draws":62,"losses":87,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":34,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":12,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":5,"wins":0},"z-ai/glm-5.2":{"draws":72,"losses":76,"wins":56},"z-ai/glm-5.3":{"draws":21,"losses":55,"wins":10},"z-ai/glm-5.3-flash":{"draws":28,"losses":48,"wins":14},"z-ai/glm-5.3-flashx":{"draws":13,"losses":19,"wins":2}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":58,"losses":55,"wins":27},"claude-fable-5":{"draws":30,"losses":62,"wins":12},"claude-fable-5-1":{"draws":8,"losses":109,"wins":1},"claude-opus-4-5":{"draws":48,"losses":73,"wins":24},"claude-opus-4-8":{"draws":10,"losses":20,"wins":2},"claude-opus-5":{"draws":4,"losses":48,"wins":4},"claude-opus-5-5":{"draws":6,"losses":20,"wins":0},"claude-sonnet-5":{"draws":49,"losses":87,"wins":26},"cohere/north-mini-code":{"draws":10,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":84,"losses":68,"wins":24},"deepseek/deepseek-v4-pro":{"draws":62,"losses":65,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":51,"losses":65,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":15,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":11},"google/gemini-3.5-flash":{"draws":39,"losses":62,"wins":27},"google/gemini-3.5-flash-lite":{"draws":107,"losses":103,"wins":94},"google/gemini-3.6-flash":{"draws":76,"losses":102,"wins":50},"google/gemini-3.8-flash":{"draws":49,"losses":55,"wins":16},"google/gemma-4-31b-it":{"draws":3,"losses":4,"wins":7},"gpt-4.1":{"draws":3,"losses":4,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":0},"gpt-5":{"draws":12,"losses":18,"wins":2},"gpt-5.4":{"draws":60,"losses":39,"wins":12},"gpt-5.4-mini":{"draws":14,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":15,"losses":12,"wins":15},"gpt-5.5":{"draws":7,"losses":21,"wins":4},"gpt-5.6-luna":{"draws":68,"losses":50,"wins":52},"gpt-5.6-sol":{"draws":18,"losses":75,"wins":18},"gpt-5.6-terra":{"draws":49,"losses":67,"wins":26},"gpt-6-astra":{"draws":9,"losses":83,"wins":0},"gpt-6-luna":{"draws":3,"losses":10,"wins":1},"gpt-6-sol":{"draws":5,"losses":20,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":14,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":63,"losses":29,"wins":38},"inclusionai/ling-3.0-flash":{"draws":23,"losses":13,"wins":29},"meituan/longcat-2.0":{"draws":31,"losses":38,"wins":32},"meta/muse-glimmer-30b":{"draws":72,"losses":54,"wins":26},"meta/muse-spark-1.2":{"draws":32,"losses":56,"wins":24},"meta/muse-spark-1.3":{"draws":44,"losses":61,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":4},"mistralai/mistral-medium-3-5":{"draws":49,"losses":19,"wins":34},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":53,"losses":64,"wins":17},"nex-agi/nex-n2-pro":{"draws":7,"losses":7,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":15,"losses":10,"wins":11},"o3":{"draws":56,"losses":72,"wins":49},"openai/gpt-oss-120b":{"draws":63,"losses":48,"wins":35},"poolside/laguna-s-2.1":{"draws":59,"losses":38,"wins":20},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":8,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":48,"losses":79,"wins":17},"qwen/qwen3.8-27b":{"draws":20,"losses":54,"wins":12},"qwen/qwen3.8-flash":{"draws":46,"losses":33,"wins":19},"qwen/qwen3.8-max":{"draws":100,"losses":113,"wins":68},"qwen/qwen3.8-max-0902":{"draws":6,"losses":8,"wins":4},"stealth/ox-alpha":{"draws":164,"losses":226,"wins":70},"stepfun/step-3.7-flash":{"draws":15,"losses":13,"wins":16},"tencent/hy3-preview":{"draws":20,"losses":13,"wins":5},"tencent/hy4-preview":{"draws":48,"losses":69,"wins":17},"thinkingmachines/inkling":{"draws":41,"losses":38,"wins":21},"thinkingmachines/inkling-small":{"draws":80,"losses":62,"wins":62},"x-ai/grok-4.5":{"draws":28,"losses":48,"wins":25},"x-ai/grok-4.6":{"draws":49,"losses":57,"wins":18},"x-ai/grok-4.7":{"draws":0,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":29,"losses":12,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":10,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":15,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":10,"wins":0},"z-ai/glm-5.2":{"draws":79,"losses":75,"wins":44},"z-ai/glm-5.3":{"draws":24,"losses":66,"wins":12},"z-ai/glm-5.3-flash":{"draws":55,"losses":70,"wins":25},"z-ai/glm-5.3-flashx":{"draws":3,"losses":10,"wins":3}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":31,"losses":14,"wins":57},"claude-fable-5":{"draws":16,"losses":55,"wins":41},"claude-fable-5-1":{"draws":1,"losses":97,"wins":10},"claude-opus-4-5":{"draws":93,"losses":72,"wins":129},"claude-opus-4-8":{"draws":28,"losses":37,"wins":43},"claude-opus-5":{"draws":33,"losses":150,"wins":45},"claude-opus-5-5":{"draws":4,"losses":37,"wins":7},"claude-sonnet-5":{"draws":69,"losses":42,"wins":99},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":33},"deepseek/deepseek-v4-flash":{"draws":29,"losses":24,"wins":73},"deepseek/deepseek-v4-pro":{"draws":26,"losses":38,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":35,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":10},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":40},"google/gemini-3.5-flash":{"draws":29,"losses":37,"wins":50},"google/gemini-3.5-flash-lite":{"draws":125,"losses":96,"wins":257},"google/gemini-3.6-flash":{"draws":100,"losses":208,"wins":190},"google/gemini-3.8-flash":{"draws":23,"losses":36,"wins":61},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":20},"gpt-4.1":{"draws":10,"losses":6,"wins":16},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":2},"gpt-5":{"draws":18,"losses":13,"wins":41},"gpt-5.4":{"draws":51,"losses":93,"wins":69},"gpt-5.4-mini":{"draws":19,"losses":5,"wins":26},"gpt-5.4-nano":{"draws":13,"losses":29,"wins":46},"gpt-5.5":{"draws":33,"losses":26,"wins":41},"gpt-5.6-luna":{"draws":49,"losses":68,"wins":83},"gpt-5.6-sol":{"draws":27,"losses":122,"wins":79},"gpt-5.6-terra":{"draws":32,"losses":26,"wins":72},"gpt-6-astra":{"draws":6,"losses":99,"wins":11},"gpt-6-luna":{"draws":7,"losses":6,"wins":11},"gpt-6-sol":{"draws":1,"losses":12,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":36,"losses":3,"wins":41},"inclusionai/ling-3.0-flash":{"draws":42,"losses":15,"wins":87},"meituan/longcat-2.0":{"draws":53,"losses":43,"wins":130},"meta/muse-glimmer-30b":{"draws":27,"losses":12,"wins":47},"meta/muse-spark-1.2":{"draws":33,"losses":40,"wins":83},"meta/muse-spark-1.3":{"draws":12,"losses":45,"wins":45},"minimax/minimax-m3":{"draws":8,"losses":4,"wins":34},"mistralai/mistral-medium-3-5":{"draws":17,"losses":8,"wins":35},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":14},"moonshotai/kimi-k3":{"draws":86,"losses":82,"wins":108},"nex-agi/nex-n2-pro":{"draws":16,"losses":1,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":2,"wins":45},"o3":{"draws":24,"losses":84,"wins":170},"openai/gpt-oss-120b":{"draws":33,"losses":9,"wins":40},"poolside/laguna-s-2.1":{"draws":67,"losses":38,"wins":123},"qwen/qwen3.7-max":{"draws":20,"losses":14,"wins":24},"qwen/qwen3.7-plus":{"draws":15,"losses":8,"wins":29},"qwen/qwen3.8-2.4t-a95b":{"draws":29,"losses":33,"wins":50},"qwen/qwen3.8-27b":{"draws":7,"losses":33,"wins":32},"qwen/qwen3.8-flash":{"draws":16,"losses":13,"wins":31},"qwen/qwen3.8-max":{"draws":35,"losses":38,"wins":48},"qwen/qwen3.8-max-0902":{"draws":4,"losses":7,"wins":7},"stealth/ox-alpha":{"draws":79,"losses":105,"wins":150},"stepfun/step-3.7-flash":{"draws":13,"losses":15,"wins":54},"tencent/hy3-preview":{"draws":13,"losses":8,"wins":33},"tencent/hy4-preview":{"draws":27,"losses":44,"wins":37},"thinkingmachines/inkling":{"draws":71,"losses":32,"wins":113},"thinkingmachines/inkling-small":{"draws":28,"losses":25,"wins":48},"x-ai/grok-4.5":{"draws":52,"losses":46,"wins":46},"x-ai/grok-4.6":{"draws":32,"losses":36,"wins":46},"x-ai/grok-4.7":{"draws":2,"losses":16,"wins":6},"x-ai/grok-build-0.1":{"draws":12,"losses":1,"wins":19},"xiaomi/mimo-v2.5":{"draws":43,"losses":15,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":27,"wins":34},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":11,"wins":7},"z-ai/glm-5.2":{"draws":47,"losses":53,"wins":82},"z-ai/glm-5.3":{"draws":28,"losses":57,"wins":21},"z-ai/glm-5.3-flash":{"draws":18,"losses":45,"wins":29},"z-ai/glm-5.3-flashx":{"draws":2,"losses":10,"wins":6}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":19,"wins":50},"claude-fable-5":{"draws":39,"losses":75,"wins":56},"claude-fable-5-1":{"draws":11,"losses":147,"wins":24},"claude-opus-4-5":{"draws":44,"losses":23,"wins":79},"claude-opus-4-8":{"draws":8,"losses":17,"wins":19},"claude-opus-5":{"draws":11,"losses":59,"wins":17},"claude-opus-5-5":{"draws":2,"losses":28,"wins":4},"claude-sonnet-5":{"draws":43,"losses":37,"wins":68},"cohere/north-mini-code":{"draws":8,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":50,"losses":17,"wins":95},"deepseek/deepseek-v4-pro":{"draws":38,"losses":33,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":53,"losses":36,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":6,"wins":15},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":12},"google/gemini-3.5-flash":{"draws":39,"losses":33,"wins":70},"google/gemini-3.5-flash-lite":{"draws":71,"losses":33,"wins":122},"google/gemini-3.6-flash":{"draws":61,"losses":69,"wins":88},"google/gemini-3.8-flash":{"draws":44,"losses":53,"wins":55},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":13},"gpt-4.1":{"draws":13,"losses":1,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":4},"gpt-5":{"draws":12,"losses":8,"wins":14},"gpt-5.4":{"draws":48,"losses":59,"wins":45},"gpt-5.4-mini":{"draws":10,"losses":4,"wins":22},"gpt-5.4-nano":{"draws":10,"losses":9,"wins":23},"gpt-5.5":{"draws":13,"losses":7,"wins":10},"gpt-5.6-luna":{"draws":39,"losses":26,"wins":67},"gpt-5.6-sol":{"draws":31,"losses":70,"wins":67},"gpt-5.6-terra":{"draws":48,"losses":25,"wins":83},"gpt-6-astra":{"draws":13,"losses":139,"wins":16},"gpt-6-luna":{"draws":4,"losses":4,"wins":10},"gpt-6-sol":{"draws":5,"losses":15,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":31,"losses":12,"wins":35},"inclusionai/ling-3.0-flash":{"draws":16,"losses":5,"wins":21},"meituan/longcat-2.0":{"draws":24,"losses":16,"wins":38},"meta/muse-glimmer-30b":{"draws":42,"losses":12,"wins":40},"meta/muse-spark-1.2":{"draws":23,"losses":21,"wins":64},"meta/muse-spark-1.3":{"draws":31,"losses":52,"wins":57},"minimax/minimax-m3":{"draws":7,"losses":0,"wins":13},"mistralai/mistral-medium-3-5":{"draws":26,"losses":4,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":46,"losses":33,"wins":59},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":2,"wins":12},"o3":{"draws":31,"losses":42,"wins":77},"openai/gpt-oss-120b":{"draws":31,"losses":13,"wins":42},"poolside/laguna-s-2.1":{"draws":31,"losses":11,"wins":36},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":2,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":45,"wins":58},"qwen/qwen3.8-27b":{"draws":20,"losses":27,"wins":29},"qwen/qwen3.8-flash":{"draws":35,"losses":18,"wins":35},"qwen/qwen3.8-max":{"draws":41,"losses":47,"wins":66},"qwen/qwen3.8-max-0902":{"draws":9,"losses":8,"wins":13},"stealth/ox-alpha":{"draws":143,"losses":162,"wins":197},"stepfun/step-3.7-flash":{"draws":7,"losses":7,"wins":18},"tencent/hy3-preview":{"draws":10,"losses":4,"wins":12},"tencent/hy4-preview":{"draws":42,"losses":41,"wins":57},"thinkingmachines/inkling":{"draws":27,"losses":8,"wins":35},"thinkingmachines/inkling-small":{"draws":49,"losses":18,"wins":57},"x-ai/grok-4.5":{"draws":32,"losses":46,"wins":36},"x-ai/grok-4.6":{"draws":38,"losses":35,"wins":35},"x-ai/grok-4.7":{"draws":3,"losses":11,"wins":6},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":6,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":2,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":12,"wins":7},"z-ai/glm-5.2":{"draws":46,"losses":33,"wins":79},"z-ai/glm-5.3":{"draws":30,"losses":74,"wins":52},"z-ai/glm-5.3-flash":{"draws":34,"losses":56,"wins":52},"z-ai/glm-5.3-flashx":{"draws":14,"losses":3,"wins":9}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":6,"wins":8},"claude-fable-5":{"draws":1,"losses":10,"wins":13},"claude-fable-5-1":{"draws":1,"losses":16,"wins":1},"claude-opus-4-5":{"draws":3,"losses":6,"wins":15},"claude-opus-4-8":{"draws":4,"losses":6,"wins":8},"claude-opus-5":{"draws":4,"losses":14,"wins":8},"claude-opus-5-5":{"draws":6,"losses":65,"wins":19},"claude-sonnet-5":{"draws":2,"losses":4,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":23},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":2,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":5,"wins":8},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":18},"google/gemini-3.5-flash-lite":{"draws":3,"losses":8,"wins":21},"google/gemini-3.6-flash":{"draws":3,"losses":6,"wins":23},"google/gemini-3.8-flash":{"draws":3,"losses":7,"wins":16},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":10},"gpt-5.4":{"draws":2,"losses":6,"wins":10},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":6},"gpt-5.4-nano":{"draws":6,"losses":1,"wins":17},"gpt-5.5":{"draws":1,"losses":12,"wins":15},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":11},"gpt-5.6-sol":{"draws":2,"losses":10,"wins":4},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":10},"gpt-6-astra":{"draws":0,"losses":11,"wins":3},"gpt-6-luna":{"draws":8,"losses":15,"wins":61},"gpt-6-sol":{"draws":12,"losses":42,"wins":36},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":1,"losses":1,"wins":10},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":5},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":16},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":10},"meta/muse-spark-1.2":{"draws":0,"losses":6,"wins":6},"meta/muse-spark-1.3":{"draws":3,"losses":4,"wins":15},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":8},"o3":{"draws":2,"losses":5,"wins":21},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":9},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":11},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":7,"wins":13},"qwen/qwen3.8-27b":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.8-flash":{"draws":0,"losses":1,"wins":9},"qwen/qwen3.8-max":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.8-max-0902":{"draws":7,"losses":0,"wins":19},"stealth/ox-alpha":{"draws":7,"losses":8,"wins":27},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":11},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":9},"tencent/hy4-preview":{"draws":0,"losses":8,"wins":10},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":8},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":16},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":11},"x-ai/grok-4.7":{"draws":0,"losses":18,"wins":18},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":4,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":12,"wins":25},"z-ai/glm-5.2":{"draws":3,"losses":7,"wins":18},"z-ai/glm-5.3":{"draws":4,"losses":9,"wins":5},"z-ai/glm-5.3-flash":{"draws":0,"losses":3,"wins":13},"z-ai/glm-5.3-flashx":{"draws":9,"losses":21,"wins":34}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":9,"wins":2},"claude-fable-5":{"draws":2,"losses":12,"wins":6},"claude-fable-5-1":{"draws":0,"losses":18,"wins":0},"claude-opus-4-5":{"draws":32,"losses":35,"wins":9},"claude-opus-4-8":{"draws":18,"losses":32,"wins":10},"claude-opus-5":{"draws":10,"losses":41,"wins":5},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":6,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":20,"losses":15,"wins":13},"deepseek/deepseek-v4-pro":{"draws":5,"losses":11,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":5,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":12,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":7,"wins":22},"google/gemini-3.5-flash":{"draws":7,"losses":14,"wins":1},"google/gemini-3.5-flash-lite":{"draws":21,"losses":14,"wins":15},"google/gemini-3.6-flash":{"draws":17,"losses":19,"wins":0},"google/gemini-3.8-flash":{"draws":0,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":11,"losses":9,"wins":18},"gpt-4.1":{"draws":11,"losses":9,"wins":6},"gpt-5":{"draws":15,"losses":17,"wins":10},"gpt-5.4":{"draws":0,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":26,"losses":18,"wins":12},"gpt-5.4-nano":{"draws":13,"losses":35,"wins":18},"gpt-5.5":{"draws":34,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":4,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":4},"gpt-6-astra":{"draws":1,"losses":11,"wins":0},"gpt-6-luna":{"draws":8,"losses":5,"wins":1},"gpt-6-sol":{"draws":5,"losses":9,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":15,"losses":1,"wins":20},"meituan/longcat-2.0":{"draws":16,"losses":17,"wins":23},"meta/muse-glimmer-30b":{"draws":6,"losses":1,"wins":5},"meta/muse-spark-1.2":{"draws":2,"losses":8,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":12,"wins":3},"minimax/minimax-m3":{"draws":16,"losses":9,"wins":19},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":15,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":16,"wins":4},"nex-agi/nex-n2-pro":{"draws":16,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":9,"wins":8},"o3":{"draws":8,"losses":20,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":23,"losses":10,"wins":17},"qwen/qwen3.7-max":{"draws":22,"losses":12,"wins":16},"qwen/qwen3.7-plus":{"draws":12,"losses":14,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":7,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":5,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":1,"wins":0},"qwen/qwen3.8-max":{"draws":8,"losses":3,"wins":1},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":14,"losses":26,"wins":6},"stepfun/step-3.7-flash":{"draws":16,"losses":3,"wins":13},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":5},"tencent/hy4-preview":{"draws":8,"losses":10,"wins":2},"thinkingmachines/inkling":{"draws":18,"losses":11,"wins":11},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":19,"wins":1},"x-ai/grok-4.6":{"draws":5,"losses":9,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":46,"losses":19,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":14,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":11,"losses":17,"wins":6},"z-ai/glm-5.3":{"draws":4,"losses":6,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":4,"wins":1},"z-ai/glm-5.3-flashx":{"draws":0,"losses":11,"wins":1}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":18,"wins":11},"claude-fable-5":{"draws":13,"losses":45,"wins":2},"claude-fable-5-1":{"draws":2,"losses":66,"wins":0},"claude-opus-4-5":{"draws":145,"losses":137,"wins":62},"claude-opus-4-8":{"draws":69,"losses":118,"wins":21},"claude-opus-5":{"draws":48,"losses":202,"wins":16},"claude-opus-5-5":{"draws":4,"losses":42,"wins":2},"claude-sonnet-5":{"draws":26,"losses":26,"wins":2},"cohere/north-mini-code":{"draws":46,"losses":29,"wins":39},"deepseek/deepseek-v4-flash":{"draws":95,"losses":58,"wins":83},"deepseek/deepseek-v4-pro":{"draws":20,"losses":24,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":21,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":21,"losses":30,"wins":3},"google/gemini-3.1-flash-lite":{"draws":66,"losses":45,"wins":77},"google/gemini-3.5-flash":{"draws":26,"losses":31,"wins":17},"google/gemini-3.5-flash-lite":{"draws":57,"losses":41,"wins":42},"google/gemini-3.6-flash":{"draws":68,"losses":82,"wins":30},"google/gemini-3.8-flash":{"draws":26,"losses":28,"wins":6},"google/gemma-4-31b-it":{"draws":35,"losses":51,"wins":52},"gpt-4.1":{"draws":40,"losses":36,"wins":20},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":0},"gpt-5":{"draws":75,"losses":54,"wins":31},"gpt-5.4":{"draws":20,"losses":19,"wins":3},"gpt-5.4-mini":{"draws":80,"losses":53,"wins":43},"gpt-5.4-nano":{"draws":71,"losses":121,"wins":106},"gpt-5.5":{"draws":92,"losses":82,"wins":22},"gpt-5.6-luna":{"draws":35,"losses":18,"wins":5},"gpt-5.6-sol":{"draws":5,"losses":41,"wins":2},"gpt-5.6-terra":{"draws":21,"losses":40,"wins":5},"gpt-6-astra":{"draws":2,"losses":44,"wins":0},"gpt-6-luna":{"draws":21,"losses":13,"wins":10},"gpt-6-sol":{"draws":8,"losses":30,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":22,"losses":5,"wins":15},"inclusionai/ling-3.0-flash":{"draws":59,"losses":29,"wins":46},"meituan/longcat-2.0":{"draws":73,"losses":74,"wins":65},"meta/muse-glimmer-30b":{"draws":34,"losses":19,"wins":13},"meta/muse-spark-1.2":{"draws":11,"losses":27,"wins":8},"meta/muse-spark-1.3":{"draws":18,"losses":47,"wins":5},"minimax/minimax-m3":{"draws":65,"losses":51,"wins":58},"mistralai/mistral-medium-3-5":{"draws":10,"losses":10,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":33,"losses":42,"wins":13},"moonshotai/kimi-k3":{"draws":29,"losses":63,"wins":12},"nex-agi/nex-n2-pro":{"draws":31,"losses":37,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":112,"losses":70,"wins":60},"o3":{"draws":37,"losses":79,"wins":20},"openai/gpt-oss-120b":{"draws":31,"losses":17,"wins":16},"poolside/laguna-s-2.1":{"draws":56,"losses":52,"wins":42},"qwen/qwen3.7-max":{"draws":66,"losses":68,"wins":28},"qwen/qwen3.7-plus":{"draws":59,"losses":47,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":24,"wins":8},"qwen/qwen3.8-27b":{"draws":9,"losses":21,"wins":4},"qwen/qwen3.8-flash":{"draws":14,"losses":17,"wins":3},"qwen/qwen3.8-max":{"draws":35,"losses":30,"wins":7},"qwen/qwen3.8-max-0902":{"draws":24,"losses":22,"wins":4},"stealth/ox-alpha":{"draws":53,"losses":107,"wins":30},"stepfun/step-3.7-flash":{"draws":54,"losses":41,"wins":43},"tencent/hy3-preview":{"draws":52,"losses":37,"wins":31},"tencent/hy4-preview":{"draws":11,"losses":47,"wins":2},"thinkingmachines/inkling":{"draws":62,"losses":39,"wins":87},"thinkingmachines/inkling-small":{"draws":29,"losses":17,"wins":12},"x-ai/grok-4.5":{"draws":43,"losses":58,"wins":15},"x-ai/grok-4.6":{"draws":28,"losses":38,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":17,"wins":1},"x-ai/grok-build-0.1":{"draws":46,"losses":39,"wins":19},"xiaomi/mimo-v2.5":{"draws":190,"losses":117,"wins":117},"xiaomi/mimo-v2.5-pro":{"draws":46,"losses":63,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":28,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":116,"losses":114,"wins":58},"z-ai/glm-5.3":{"draws":15,"losses":27,"wins":0},"z-ai/glm-5.3-flash":{"draws":12,"losses":35,"wins":13},"z-ai/glm-5.3-flashx":{"draws":18,"losses":20,"wins":2}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":6,"wins":11},"claude-fable-5":{"draws":0,"losses":20,"wins":2},"claude-fable-5-1":{"draws":0,"losses":22,"wins":0},"claude-opus-4-5":{"draws":25,"losses":50,"wins":47},"claude-opus-4-8":{"draws":20,"losses":38,"wins":24},"claude-opus-5":{"draws":18,"losses":82,"wins":6},"claude-opus-5-5":{"draws":0,"losses":14,"wins":0},"claude-sonnet-5":{"draws":2,"losses":12,"wins":14},"cohere/north-mini-code":{"draws":15,"losses":10,"wins":23},"deepseek/deepseek-v4-flash":{"draws":27,"losses":21,"wins":26},"deepseek/deepseek-v4-pro":{"draws":7,"losses":14,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":8,"wins":3},"google/gemini-3.1-flash-lite":{"draws":18,"losses":5,"wins":47},"google/gemini-3.5-flash":{"draws":7,"losses":10,"wins":19},"google/gemini-3.5-flash-lite":{"draws":22,"losses":17,"wins":31},"google/gemini-3.6-flash":{"draws":24,"losses":37,"wins":23},"google/gemini-3.8-flash":{"draws":11,"losses":17,"wins":8},"google/gemma-4-31b-it":{"draws":6,"losses":9,"wins":19},"gpt-4.1":{"draws":5,"losses":18,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":18,"losses":21,"wins":21},"gpt-5.4":{"draws":8,"losses":31,"wins":5},"gpt-5.4-mini":{"draws":9,"losses":22,"wins":17},"gpt-5.4-nano":{"draws":26,"losses":32,"wins":48},"gpt-5.5":{"draws":19,"losses":30,"wins":23},"gpt-5.6-luna":{"draws":10,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":8},"gpt-5.6-terra":{"draws":6,"losses":12,"wins":4},"gpt-6-astra":{"draws":2,"losses":28,"wins":2},"gpt-6-luna":{"draws":6,"losses":4,"wins":0},"gpt-6-sol":{"draws":1,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":8,"losses":9,"wins":7},"inclusionai/ling-3.0-flash":{"draws":21,"losses":15,"wins":26},"meituan/longcat-2.0":{"draws":32,"losses":26,"wins":34},"meta/muse-glimmer-30b":{"draws":7,"losses":9,"wins":10},"meta/muse-spark-1.2":{"draws":7,"losses":23,"wins":18},"meta/muse-spark-1.3":{"draws":0,"losses":22,"wins":2},"minimax/minimax-m3":{"draws":15,"losses":18,"wins":23},"mistralai/mistral-medium-3-5":{"draws":12,"losses":3,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":14,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":21,"wins":20},"nex-agi/nex-n2-pro":{"draws":12,"losses":14,"wins":22},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":16,"wins":26},"o3":{"draws":14,"losses":25,"wins":43},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":10},"poolside/laguna-s-2.1":{"draws":19,"losses":20,"wins":29},"qwen/qwen3.7-max":{"draws":17,"losses":28,"wins":15},"qwen/qwen3.7-plus":{"draws":23,"losses":9,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":19,"wins":9},"qwen/qwen3.8-27b":{"draws":11,"losses":17,"wins":8},"qwen/qwen3.8-flash":{"draws":6,"losses":15,"wins":9},"qwen/qwen3.8-max":{"draws":4,"losses":13,"wins":9},"qwen/qwen3.8-max-0902":{"draws":3,"losses":6,"wins":5},"stealth/ox-alpha":{"draws":12,"losses":49,"wins":31},"stepfun/step-3.7-flash":{"draws":12,"losses":13,"wins":23},"tencent/hy3-preview":{"draws":16,"losses":21,"wins":15},"tencent/hy4-preview":{"draws":2,"losses":14,"wins":4},"thinkingmachines/inkling":{"draws":13,"losses":17,"wins":34},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":10},"x-ai/grok-4.5":{"draws":9,"losses":34,"wins":27},"x-ai/grok-4.6":{"draws":7,"losses":22,"wins":7},"x-ai/grok-4.7":{"draws":0,"losses":7,"wins":1},"x-ai/grok-build-0.1":{"draws":11,"losses":3,"wins":14},"xiaomi/mimo-v2.5":{"draws":46,"losses":31,"wins":63},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":10,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":2},"z-ai/glm-5.2":{"draws":41,"losses":44,"wins":35},"z-ai/glm-5.3":{"draws":10,"losses":20,"wins":4},"z-ai/glm-5.3-flash":{"draws":10,"losses":16,"wins":6},"z-ai/glm-5.3-flashx":{"draws":3,"losses":5,"wins":0}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":4,"wins":4},"claude-fable-5":{"draws":3,"losses":10,"wins":3},"claude-fable-5-1":{"draws":2,"losses":23,"wins":5},"claude-opus-4-5":{"draws":4,"losses":7,"wins":7},"claude-opus-4-8":{"draws":3,"losses":3,"wins":8},"claude-opus-5":{"draws":2,"losses":14,"wins":2},"claude-opus-5-5":{"draws":5,"losses":54,"wins":1},"claude-sonnet-5":{"draws":8,"losses":4,"wins":10},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":11},"deepseek/deepseek-v4-flash":{"draws":12,"losses":3,"wins":19},"deepseek/deepseek-v4-pro":{"draws":3,"losses":1,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":9,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":12,"wins":9},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":9},"google/gemini-3.5-flash-lite":{"draws":5,"losses":3,"wins":10},"google/gemini-3.6-flash":{"draws":3,"losses":18,"wins":15},"google/gemini-3.8-flash":{"draws":4,"losses":4,"wins":8},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":1},"gpt-4.1":{"draws":6,"losses":1,"wins":5},"gpt-5":{"draws":9,"losses":1,"wins":4},"gpt-5.4":{"draws":0,"losses":10,"wins":8},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":9},"gpt-5.4-nano":{"draws":9,"losses":0,"wins":9},"gpt-5.5":{"draws":5,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":11,"losses":6,"wins":5},"gpt-5.6-sol":{"draws":2,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":1,"losses":5,"wins":6},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"gpt-6-luna":{"draws":16,"losses":23,"wins":19},"gpt-6-sol":{"draws":10,"losses":43,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":7,"losses":2,"wins":1},"meta/muse-glimmer-30b":{"draws":4,"losses":4,"wins":6},"meta/muse-spark-1.2":{"draws":1,"losses":10,"wins":3},"meta/muse-spark-1.3":{"draws":8,"losses":11,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":8,"wins":11},"o3":{"draws":5,"losses":8,"wins":19},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":4},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":7,"wins":4},"qwen/qwen3.8-27b":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":5},"qwen/qwen3.8-max":{"draws":4,"losses":8,"wins":14},"qwen/qwen3.8-max-0902":{"draws":13,"losses":21,"wins":30},"stealth/ox-alpha":{"draws":9,"losses":28,"wins":27},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":6},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":6},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":12},"thinkingmachines/inkling-small":{"draws":6,"losses":1,"wins":15},"x-ai/grok-4.5":{"draws":1,"losses":6,"wins":3},"x-ai/grok-4.6":{"draws":4,"losses":10,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":18,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":7,"losses":3,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":11,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":14,"wins":9},"z-ai/glm-5.2":{"draws":9,"losses":8,"wins":9},"z-ai/glm-5.3":{"draws":5,"losses":10,"wins":1},"z-ai/glm-5.3-flash":{"draws":5,"losses":3,"wins":6},"z-ai/glm-5.3-flashx":{"draws":15,"losses":31,"wins":30}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":7,"wins":14},"claude-fable-5":{"draws":1,"losses":16,"wins":5},"claude-fable-5-1":{"draws":1,"losses":13,"wins":6},"claude-opus-4-5":{"draws":0,"losses":2,"wins":12},"claude-opus-4-8":{"draws":0,"losses":8,"wins":10},"claude-opus-5":{"draws":5,"losses":6,"wins":5},"claude-opus-5-5":{"draws":15,"losses":50,"wins":11},"claude-sonnet-5":{"draws":5,"losses":5,"wins":8},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":9},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":4,"wins":9},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":8},"google/gemini-3.5-flash-lite":{"draws":2,"losses":3,"wins":7},"google/gemini-3.6-flash":{"draws":5,"losses":10,"wins":9},"google/gemini-3.8-flash":{"draws":4,"losses":1,"wins":9},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":4,"losses":1,"wins":5},"gpt-5":{"draws":4,"losses":2,"wins":6},"gpt-5.4":{"draws":2,"losses":9,"wins":9},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":10},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":12},"gpt-5.5":{"draws":4,"losses":3,"wins":5},"gpt-5.6-luna":{"draws":3,"losses":5,"wins":6},"gpt-5.6-sol":{"draws":9,"losses":5,"wins":2},"gpt-5.6-terra":{"draws":4,"losses":6,"wins":10},"gpt-6-astra":{"draws":1,"losses":7,"wins":2},"gpt-6-luna":{"draws":19,"losses":17,"wins":36},"gpt-6-sol":{"draws":18,"losses":36,"wins":16},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":8,"losses":1,"wins":7},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":1,"losses":1,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":6},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":5},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":9},"o3":{"draws":0,"losses":6,"wins":8},"openai/gpt-oss-120b":{"draws":1,"losses":2,"wins":7},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":5},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":4,"wins":9},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":6},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":2},"qwen/qwen3.8-max":{"draws":9,"losses":9,"wins":4},"qwen/qwen3.8-max-0902":{"draws":9,"losses":13,"wins":14},"stealth/ox-alpha":{"draws":9,"losses":14,"wins":19},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":12},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":8},"tencent/hy4-preview":{"draws":6,"losses":4,"wins":8},"thinkingmachines/inkling":{"draws":9,"losses":0,"wins":5},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":7,"wins":11},"x-ai/grok-4.6":{"draws":5,"losses":7,"wins":12},"x-ai/grok-4.7":{"draws":9,"losses":25,"wins":12},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":9,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":8,"losses":6,"wins":8},"z-ai/glm-5.3":{"draws":5,"losses":8,"wins":7},"z-ai/glm-5.3-flash":{"draws":3,"losses":3,"wins":0},"z-ai/glm-5.3-flashx":{"draws":12,"losses":23,"wins":27}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":78,"losses":55,"wins":49},"claude-fable-5":{"draws":47,"losses":78,"wins":29},"claude-fable-5-1":{"draws":18,"losses":107,"wins":3},"claude-opus-4-5":{"draws":104,"losses":143,"wins":95},"claude-opus-4-8":{"draws":68,"losses":91,"wins":53},"claude-opus-5":{"draws":53,"losses":182,"wins":25},"claude-opus-5-5":{"draws":3,"losses":53,"wins":2},"claude-sonnet-5":{"draws":64,"losses":78,"wins":54},"cohere/north-mini-code":{"draws":21,"losses":14,"wins":45},"deepseek/deepseek-v4-flash":{"draws":101,"losses":61,"wins":104},"deepseek/deepseek-v4-pro":{"draws":58,"losses":65,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":60,"losses":72,"wins":52},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":21,"wins":14},"google/gemini-3.1-flash-lite":{"draws":40,"losses":19,"wins":73},"google/gemini-3.5-flash":{"draws":66,"losses":72,"wins":76},"google/gemini-3.5-flash-lite":{"draws":137,"losses":105,"wins":112},"google/gemini-3.6-flash":{"draws":93,"losses":122,"wins":87},"google/gemini-3.8-flash":{"draws":46,"losses":90,"wins":40},"google/gemma-4-31b-it":{"draws":30,"losses":12,"wins":24},"gpt-4.1":{"draws":17,"losses":18,"wins":27},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":4},"gpt-5":{"draws":53,"losses":50,"wins":47},"gpt-5.4":{"draws":58,"losses":62,"wins":36},"gpt-5.4-mini":{"draws":71,"losses":20,"wins":41},"gpt-5.4-nano":{"draws":57,"losses":60,"wins":67},"gpt-5.5":{"draws":71,"losses":75,"wins":36},"gpt-5.6-luna":{"draws":73,"losses":37,"wins":60},"gpt-5.6-sol":{"draws":19,"losses":119,"wins":30},"gpt-5.6-terra":{"draws":86,"losses":70,"wins":40},"gpt-6-astra":{"draws":11,"losses":123,"wins":4},"gpt-6-luna":{"draws":12,"losses":14,"wins":20},"gpt-6-sol":{"draws":5,"losses":36,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":16,"losses":2,"wins":8},"inception/mercury-2.5-preview":{"draws":63,"losses":20,"wins":67},"inclusionai/ling-3.0-flash":{"draws":62,"losses":17,"wins":31},"meituan/longcat-2.0":{"draws":64,"losses":60,"wins":84},"meta/muse-glimmer-30b":{"draws":74,"losses":33,"wins":59},"meta/muse-spark-1.2":{"draws":31,"losses":66,"wins":53},"meta/muse-spark-1.3":{"draws":36,"losses":51,"wins":37},"minimax/minimax-m3":{"draws":37,"losses":19,"wins":32},"mistralai/mistral-medium-3-5":{"draws":52,"losses":19,"wins":53},"moonshotai/kimi-k2.7-code":{"draws":11,"losses":19,"wins":20},"moonshotai/kimi-k3":{"draws":68,"losses":55,"wins":35},"nex-agi/nex-n2-pro":{"draws":46,"losses":15,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":90,"losses":29,"wins":51},"o3":{"draws":40,"losses":99,"wins":89},"openai/gpt-oss-120b":{"draws":73,"losses":32,"wins":63},"poolside/laguna-s-2.1":{"draws":110,"losses":48,"wins":62},"qwen/qwen3.7-max":{"draws":46,"losses":27,"wins":45},"qwen/qwen3.7-plus":{"draws":47,"losses":18,"wins":47},"qwen/qwen3.8-2.4t-a95b":{"draws":67,"losses":67,"wins":52},"qwen/qwen3.8-27b":{"draws":35,"losses":45,"wins":38},"qwen/qwen3.8-flash":{"draws":49,"losses":44,"wins":25},"qwen/qwen3.8-max":{"draws":64,"losses":53,"wins":45},"qwen/qwen3.8-max-0902":{"draws":15,"losses":25,"wins":6},"stealth/ox-alpha":{"draws":167,"losses":262,"wins":141},"stepfun/step-3.7-flash":{"draws":26,"losses":23,"wins":47},"tencent/hy3-preview":{"draws":43,"losses":26,"wins":33},"tencent/hy4-preview":{"draws":52,"losses":77,"wins":35},"thinkingmachines/inkling":{"draws":72,"losses":56,"wins":76},"thinkingmachines/inkling-small":{"draws":79,"losses":44,"wins":75},"x-ai/grok-4.5":{"draws":47,"losses":82,"wins":53},"x-ai/grok-4.6":{"draws":46,"losses":79,"wins":33},"x-ai/grok-4.7":{"draws":3,"losses":18,"wins":7},"x-ai/grok-build-0.1":{"draws":11,"losses":6,"wins":17},"xiaomi/mimo-v2.5":{"draws":116,"losses":58,"wins":114},"xiaomi/mimo-v2.5-pro":{"draws":41,"losses":35,"wins":44},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":9,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":116,"losses":90,"wins":90},"z-ai/glm-5.3":{"draws":47,"losses":80,"wins":25},"z-ai/glm-5.3-flash":{"draws":63,"losses":74,"wins":35},"z-ai/glm-5.3-flashx":{"draws":9,"losses":14,"wins":13}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":13,"wins":58},"claude-fable-5":{"draws":22,"losses":55,"wins":77},"claude-fable-5-1":{"draws":10,"losses":130,"wins":30},"claude-opus-4-5":{"draws":33,"losses":22,"wins":93},"claude-opus-4-8":{"draws":11,"losses":11,"wins":20},"claude-opus-5":{"draws":15,"losses":49,"wins":20},"claude-opus-5-5":{"draws":1,"losses":21,"wins":4},"claude-sonnet-5":{"draws":27,"losses":16,"wins":105},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":36,"losses":7,"wins":75},"deepseek/deepseek-v4-pro":{"draws":24,"losses":22,"wins":76},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":25,"wins":65},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":8,"wins":14},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":18},"google/gemini-3.5-flash":{"draws":26,"losses":33,"wins":83},"google/gemini-3.5-flash-lite":{"draws":44,"losses":17,"wins":155},"google/gemini-3.6-flash":{"draws":33,"losses":43,"wins":140},"google/gemini-3.8-flash":{"draws":23,"losses":39,"wins":88},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":13},"gpt-4.1":{"draws":1,"losses":0,"wins":7},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":5},"gpt-5":{"draws":5,"losses":3,"wins":22},"gpt-5.4":{"draws":31,"losses":57,"wins":74},"gpt-5.4-mini":{"draws":7,"losses":1,"wins":22},"gpt-5.4-nano":{"draws":7,"losses":12,"wins":35},"gpt-5.5":{"draws":8,"losses":10,"wins":18},"gpt-5.6-luna":{"draws":33,"losses":17,"wins":68},"gpt-5.6-sol":{"draws":26,"losses":68,"wins":66},"gpt-5.6-terra":{"draws":41,"losses":17,"wins":72},"gpt-6-astra":{"draws":23,"losses":116,"wins":13},"gpt-6-luna":{"draws":4,"losses":3,"wins":11},"gpt-6-sol":{"draws":6,"losses":10,"wins":16},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":30,"losses":4,"wins":34},"inclusionai/ling-3.0-flash":{"draws":15,"losses":0,"wins":25},"meituan/longcat-2.0":{"draws":24,"losses":6,"wins":50},"meta/muse-glimmer-30b":{"draws":17,"losses":12,"wins":39},"meta/muse-spark-1.2":{"draws":21,"losses":24,"wins":57},"meta/muse-spark-1.3":{"draws":28,"losses":33,"wins":77},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":10},"mistralai/mistral-medium-3-5":{"draws":23,"losses":7,"wins":28},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":31,"losses":27,"wins":72},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":25},"o3":{"draws":10,"losses":28,"wins":104},"openai/gpt-oss-120b":{"draws":32,"losses":6,"wins":40},"poolside/laguna-s-2.1":{"draws":27,"losses":5,"wins":44},"qwen/qwen3.7-max":{"draws":6,"losses":5,"wins":9},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":29,"wins":76},"qwen/qwen3.8-27b":{"draws":11,"losses":13,"wins":42},"qwen/qwen3.8-flash":{"draws":24,"losses":14,"wins":56},"qwen/qwen3.8-max":{"draws":32,"losses":28,"wins":68},"qwen/qwen3.8-max-0902":{"draws":11,"losses":4,"wins":17},"stealth/ox-alpha":{"draws":89,"losses":116,"wins":241},"stepfun/step-3.7-flash":{"draws":10,"losses":2,"wins":24},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":21,"losses":26,"wins":89},"thinkingmachines/inkling":{"draws":21,"losses":10,"wins":55},"thinkingmachines/inkling-small":{"draws":24,"losses":12,"wins":66},"x-ai/grok-4.5":{"draws":28,"losses":21,"wins":57},"x-ai/grok-4.6":{"draws":30,"losses":52,"wins":74},"x-ai/grok-4.7":{"draws":4,"losses":5,"wins":9},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":15,"losses":0,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":4,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":1,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":7,"wins":8},"z-ai/glm-5.2":{"draws":47,"losses":25,"wins":80},"z-ai/glm-5.3":{"draws":18,"losses":37,"wins":37},"z-ai/glm-5.3-flash":{"draws":27,"losses":29,"wins":76},"z-ai/glm-5.3-flashx":{"draws":6,"losses":3,"wins":21}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":16,"wins":53},"claude-fable-5":{"draws":27,"losses":76,"wins":45},"claude-fable-5-1":{"draws":16,"losses":135,"wins":17},"claude-opus-4-5":{"draws":39,"losses":38,"wins":73},"claude-opus-4-8":{"draws":8,"losses":14,"wins":16},"claude-opus-5":{"draws":8,"losses":78,"wins":20},"claude-opus-5-5":{"draws":7,"losses":28,"wins":1},"claude-sonnet-5":{"draws":32,"losses":37,"wins":77},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":41,"losses":27,"wins":56},"deepseek/deepseek-v4-pro":{"draws":40,"losses":36,"wins":54},"deepseek/deepseek-v4-pro-0813":{"draws":39,"losses":38,"wins":57},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":11,"wins":8},"google/gemini-3.1-flash-lite":{"draws":1,"losses":4,"wins":15},"google/gemini-3.5-flash":{"draws":46,"losses":54,"wins":52},"google/gemini-3.5-flash-lite":{"draws":65,"losses":42,"wins":117},"google/gemini-3.6-flash":{"draws":54,"losses":70,"wins":98},"google/gemini-3.8-flash":{"draws":39,"losses":67,"wins":50},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":18},"gpt-4.1":{"draws":1,"losses":2,"wins":5},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":18,"losses":10,"wins":18},"gpt-5.4":{"draws":31,"losses":56,"wins":45},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":10},"gpt-5.4-nano":{"draws":3,"losses":3,"wins":16},"gpt-5.5":{"draws":8,"losses":14,"wins":16},"gpt-5.6-luna":{"draws":38,"losses":35,"wins":49},"gpt-5.6-sol":{"draws":30,"losses":77,"wins":57},"gpt-5.6-terra":{"draws":37,"losses":33,"wins":60},"gpt-6-astra":{"draws":24,"losses":118,"wins":10},"gpt-6-luna":{"draws":4,"losses":5,"wins":15},"gpt-6-sol":{"draws":6,"losses":15,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":35,"losses":10,"wins":43},"inclusionai/ling-3.0-flash":{"draws":9,"losses":6,"wins":25},"meituan/longcat-2.0":{"draws":24,"losses":23,"wins":43},"meta/muse-glimmer-30b":{"draws":40,"losses":13,"wins":59},"meta/muse-spark-1.2":{"draws":16,"losses":39,"wins":45},"meta/muse-spark-1.3":{"draws":28,"losses":43,"wins":55},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":12},"mistralai/mistral-medium-3-5":{"draws":23,"losses":14,"wins":31},"moonshotai/kimi-k3":{"draws":49,"losses":33,"wins":50},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":3,"wins":16},"o3":{"draws":30,"losses":58,"wins":64},"openai/gpt-oss-120b":{"draws":34,"losses":9,"wins":57},"poolside/laguna-s-2.1":{"draws":42,"losses":14,"wins":46},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":38,"losses":54,"wins":48},"qwen/qwen3.8-27b":{"draws":25,"losses":33,"wins":34},"qwen/qwen3.8-flash":{"draws":29,"losses":31,"wins":26},"qwen/qwen3.8-max":{"draws":42,"losses":53,"wins":47},"qwen/qwen3.8-max-0902":{"draws":1,"losses":9,"wins":8},"stealth/ox-alpha":{"draws":118,"losses":179,"wins":190},"stepfun/step-3.7-flash":{"draws":17,"losses":6,"wins":19},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":15},"tencent/hy4-preview":{"draws":31,"losses":38,"wins":51},"thinkingmachines/inkling":{"draws":28,"losses":14,"wins":48},"thinkingmachines/inkling-small":{"draws":55,"losses":25,"wins":70},"x-ai/grok-4.5":{"draws":18,"losses":29,"wins":45},"x-ai/grok-4.6":{"draws":34,"losses":52,"wins":56},"x-ai/grok-4.7":{"draws":0,"losses":13,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":4},"xiaomi/mimo-v2.5":{"draws":12,"losses":13,"wins":35},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":6,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":63,"losses":35,"wins":74},"z-ai/glm-5.3":{"draws":27,"losses":76,"wins":29},"z-ai/glm-5.3-flash":{"draws":34,"losses":33,"wins":33},"z-ai/glm-5.3-flashx":{"draws":5,"losses":4,"wins":13}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":15},"claude-fable-5":{"draws":6,"losses":11,"wins":11},"claude-fable-5-1":{"draws":4,"losses":36,"wins":4},"claude-opus-4-5":{"draws":5,"losses":1,"wins":16},"claude-opus-4-8":{"draws":4,"losses":9,"wins":7},"claude-opus-5":{"draws":6,"losses":24,"wins":6},"claude-opus-5-5":{"draws":14,"losses":96,"wins":8},"claude-sonnet-5":{"draws":11,"losses":8,"wins":3},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":8,"losses":2,"wins":16},"deepseek/deepseek-v4-pro":{"draws":5,"losses":5,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":17,"losses":10,"wins":21},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":27},"google/gemini-3.5-flash":{"draws":11,"losses":8,"wins":9},"google/gemini-3.5-flash-lite":{"draws":7,"losses":5,"wins":30},"google/gemini-3.6-flash":{"draws":16,"losses":19,"wins":13},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":12},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":8,"losses":4,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":2,"wins":6},"gpt-5.4":{"draws":7,"losses":6,"wins":7},"gpt-5.4-mini":{"draws":3,"losses":5,"wins":14},"gpt-5.4-nano":{"draws":8,"losses":10,"wins":18},"gpt-5.5":{"draws":16,"losses":8,"wins":4},"gpt-5.6-luna":{"draws":3,"losses":4,"wins":13},"gpt-5.6-sol":{"draws":7,"losses":6,"wins":7},"gpt-5.6-terra":{"draws":5,"losses":10,"wins":5},"gpt-6-astra":{"draws":2,"losses":22,"wins":2},"gpt-6-luna":{"draws":27,"losses":24,"wins":53},"gpt-6-sol":{"draws":20,"losses":65,"wins":29},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":7,"losses":0,"wins":9},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":20},"meituan/longcat-2.0":{"draws":17,"losses":5,"wins":11},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":7},"meta/muse-spark-1.2":{"draws":5,"losses":10,"wins":9},"meta/muse-spark-1.3":{"draws":13,"losses":3,"wins":8},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":15},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":6,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":9,"wins":11},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":14},"o3":{"draws":1,"losses":12,"wins":31},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":13},"poolside/laguna-s-2.1":{"draws":6,"losses":5,"wins":9},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":9},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":10,"wins":14},"qwen/qwen3.8-27b":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":13},"qwen/qwen3.8-max":{"draws":14,"losses":6,"wins":6},"qwen/qwen3.8-max-0902":{"draws":20,"losses":36,"wins":30},"stealth/ox-alpha":{"draws":15,"losses":41,"wins":46},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":5},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":4},"tencent/hy4-preview":{"draws":1,"losses":11,"wins":6},"thinkingmachines/inkling":{"draws":13,"losses":2,"wins":19},"thinkingmachines/inkling-small":{"draws":3,"losses":3,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":9,"wins":3},"x-ai/grok-4.7":{"draws":9,"losses":34,"wins":21},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":18,"losses":2,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":30,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":12,"losses":27,"wins":23},"z-ai/glm-5.2":{"draws":9,"losses":13,"wins":14},"z-ai/glm-5.3":{"draws":6,"losses":21,"wins":3},"z-ai/glm-5.3-flash":{"draws":5,"losses":13,"wins":4},"z-ai/glm-5.3-flashx":{"draws":16,"losses":26,"wins":26}}},"versus_totals_tracks":{"highest":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":11,"wins":14},"claude-fable-5":{"draws":10,"losses":26,"wins":4},"claude-fable-5-1":{"draws":2,"losses":43,"wins":1},"claude-opus-4-5":{"draws":19,"losses":22,"wins":5},"claude-opus-4-8":{"draws":0,"losses":3,"wins":1},"claude-opus-5":{"draws":0,"losses":19,"wins":7},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":17,"losses":20,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":22,"losses":16,"wins":16},"deepseek/deepseek-v4-pro":{"draws":10,"losses":25,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":18,"losses":23,"wins":13},"google/gemini-3.5-flash-lite":{"draws":42,"losses":20,"wins":28},"google/gemini-3.6-flash":{"draws":24,"losses":30,"wins":18},"google/gemini-3.8-flash":{"draws":17,"losses":21,"wins":8},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":8,"wins":6},"gpt-5.4":{"draws":13,"losses":15,"wins":10},"gpt-5.4-mini":{"draws":3,"losses":3,"wins":6},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":5},"gpt-5.5":{"draws":12,"losses":8,"wins":6},"gpt-5.6-luna":{"draws":27,"losses":14,"wins":17},"gpt-5.6-sol":{"draws":3,"losses":25,"wins":8},"gpt-5.6-terra":{"draws":18,"losses":15,"wins":11},"gpt-6-astra":{"draws":1,"losses":24,"wins":1},"gpt-6-luna":{"draws":0,"losses":0,"wins":4},"gpt-6-sol":{"draws":0,"losses":3,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":7},"inception/mercury-2.5-preview":{"draws":19,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":8},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":15},"meta/muse-glimmer-30b":{"draws":24,"losses":10,"wins":18},"meta/muse-spark-1.2":{"draws":10,"losses":11,"wins":9},"meta/muse-spark-1.3":{"draws":12,"losses":22,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":9},"mistralai/mistral-medium-3-5":{"draws":14,"losses":5,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":12,"losses":15,"wins":7},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":4,"wins":5},"o3":{"draws":10,"losses":19,"wins":21},"openai/gpt-oss-120b":{"draws":27,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":21,"losses":5,"wins":10},"qwen/qwen3.7-max":{"draws":1,"losses":7,"wins":2},"qwen/qwen3.7-plus":{"draws":5,"losses":1,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":11,"wins":14},"qwen/qwen3.8-27b":{"draws":4,"losses":12,"wins":8},"qwen/qwen3.8-flash":{"draws":17,"losses":9,"wins":6},"qwen/qwen3.8-max":{"draws":19,"losses":18,"wins":19},"qwen/qwen3.8-max-0902":{"draws":5,"losses":4,"wins":1},"stealth/ox-alpha":{"draws":46,"losses":75,"wins":33},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":10},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":4},"tencent/hy4-preview":{"draws":20,"losses":30,"wins":8},"thinkingmachines/inkling":{"draws":19,"losses":8,"wins":23},"thinkingmachines/inkling-small":{"draws":24,"losses":9,"wins":19},"x-ai/grok-4.5":{"draws":15,"losses":21,"wins":6},"x-ai/grok-4.6":{"draws":11,"losses":26,"wins":7},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":9,"losses":3,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":3,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":31,"losses":19,"wins":28},"z-ai/glm-5.3":{"draws":9,"losses":21,"wins":4},"z-ai/glm-5.3-flash":{"draws":14,"losses":20,"wins":6},"z-ai/glm-5.3-flashx":{"draws":2,"losses":2,"wins":0}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":17},"claude-fable-5":{"draws":2,"losses":16,"wins":16},"claude-fable-5-1":{"draws":4,"losses":48,"wins":14},"claude-opus-4-5":{"draws":7,"losses":4,"wins":45},"claude-opus-4-8":{"draws":1,"losses":4,"wins":9},"claude-opus-5":{"draws":4,"losses":14,"wins":14},"claude-opus-5-5":{"draws":0,"losses":3,"wins":1},"claude-sonnet-5":{"draws":9,"losses":5,"wins":32},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":4,"losses":1,"wins":31},"deepseek/deepseek-v4-pro":{"draws":2,"losses":11,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":4,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":2,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":1},"google/gemini-3.5-flash":{"draws":9,"losses":5,"wins":44},"google/gemini-3.5-flash-lite":{"draws":7,"losses":6,"wins":63},"google/gemini-3.6-flash":{"draws":11,"losses":12,"wins":35},"google/gemini-3.8-flash":{"draws":10,"losses":20,"wins":24},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":5},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":5,"wins":7},"gpt-5.4":{"draws":8,"losses":17,"wins":11},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":8},"gpt-5.5":{"draws":0,"losses":5,"wins":3},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":18},"gpt-5.6-sol":{"draws":8,"losses":19,"wins":37},"gpt-5.6-terra":{"draws":12,"losses":5,"wins":25},"gpt-6-astra":{"draws":5,"losses":46,"wins":11},"gpt-6-luna":{"draws":2,"losses":1,"wins":1},"gpt-6-sol":{"draws":1,"losses":4,"wins":1},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":11},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":7},"meituan/longcat-2.0":{"draws":2,"losses":7,"wins":14},"meta/muse-glimmer-30b":{"draws":6,"losses":1,"wins":19},"meta/muse-spark-1.2":{"draws":3,"losses":4,"wins":19},"meta/muse-spark-1.3":{"draws":7,"losses":13,"wins":24},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":5,"losses":4,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":27},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":6},"o3":{"draws":4,"losses":8,"wins":32},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":20},"poolside/laguna-s-2.1":{"draws":7,"losses":0,"wins":21},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":5},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":23},"qwen/qwen3.8-27b":{"draws":2,"losses":3,"wins":21},"qwen/qwen3.8-flash":{"draws":11,"losses":3,"wins":16},"qwen/qwen3.8-max":{"draws":8,"losses":8,"wins":28},"qwen/qwen3.8-max-0902":{"draws":0,"losses":0,"wins":6},"stealth/ox-alpha":{"draws":30,"losses":26,"wins":110},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":8,"losses":10,"wins":28},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":20},"thinkingmachines/inkling-small":{"draws":5,"losses":1,"wins":26},"x-ai/grok-4.5":{"draws":1,"losses":9,"wins":22},"x-ai/grok-4.6":{"draws":13,"losses":16,"wins":37},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":6},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":0,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":10,"losses":4,"wins":26},"z-ai/glm-5.3":{"draws":8,"losses":18,"wins":28},"z-ai/glm-5.3-flash":{"draws":8,"losses":9,"wins":37},"z-ai/glm-5.3-flashx":{"draws":0,"losses":2,"wins":2}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":42},"claude-fable-5":{"draws":1,"losses":6,"wins":63},"claude-fable-5-1":{"draws":4,"losses":20,"wins":56},"claude-opus-4-5":{"draws":1,"losses":2,"wins":57},"claude-opus-4-8":{"draws":0,"losses":0,"wins":8},"claude-opus-5":{"draws":0,"losses":6,"wins":18},"claude-opus-5-5":{"draws":3,"losses":3,"wins":6},"claude-sonnet-5":{"draws":0,"losses":1,"wins":69},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":50},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":51},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":1,"wins":50},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":4,"wins":11},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":56},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":79},"google/gemini-3.6-flash":{"draws":6,"losses":5,"wins":79},"google/gemini-3.8-flash":{"draws":5,"losses":4,"wins":65},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":0,"losses":0,"wins":20},"gpt-5.4":{"draws":0,"losses":3,"wins":53},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":10},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":6},"gpt-5.5":{"draws":0,"losses":0,"wins":16},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":45},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":67},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":60},"gpt-6-astra":{"draws":5,"losses":32,"wins":45},"gpt-6-luna":{"draws":0,"losses":0,"wins":2},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":18},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":20},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":18},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":30},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":38},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":60},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":5},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":57},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":20},"o3":{"draws":0,"losses":0,"wins":48},"openai/gpt-oss-120b":{"draws":2,"losses":1,"wins":25},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":27},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":12},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":0,"wins":54},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":28},"qwen/qwen3.8-flash":{"draws":1,"losses":0,"wins":35},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":65},"qwen/qwen3.8-max-0902":{"draws":0,"losses":5,"wins":3},"stealth/ox-alpha":{"draws":14,"losses":7,"wins":215},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":10},"tencent/hy4-preview":{"draws":1,"losses":1,"wins":62},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":37},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"x-ai/grok-4.5":{"draws":0,"losses":1,"wins":41},"x-ai/grok-4.6":{"draws":2,"losses":7,"wins":71},"x-ai/grok-4.7":{"draws":0,"losses":0,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":44},"z-ai/glm-5.3":{"draws":2,"losses":6,"wins":60},"z-ai/glm-5.3-flash":{"draws":1,"losses":7,"wins":58},"z-ai/glm-5.3-flashx":{"draws":1,"losses":1,"wins":20}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":7,"wins":30},"claude-fable-5":{"draws":12,"losses":38,"wins":8},"claude-fable-5-1":{"draws":2,"losses":55,"wins":3},"claude-opus-4-5":{"draws":17,"losses":26,"wins":15},"claude-opus-4-8":{"draws":4,"losses":18,"wins":6},"claude-opus-5":{"draws":11,"losses":83,"wins":4},"claude-opus-5-5":{"draws":2,"losses":10,"wins":0},"claude-sonnet-5":{"draws":45,"losses":18,"wins":47},"cohere/north-mini-code":{"draws":2,"losses":6,"wins":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":9,"wins":22},"deepseek/deepseek-v4-pro":{"draws":13,"losses":15,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":21,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":16},"google/gemini-3.5-flash":{"draws":11,"losses":28,"wins":19},"google/gemini-3.5-flash-lite":{"draws":85,"losses":48,"wins":93},"google/gemini-3.6-flash":{"draws":54,"losses":94,"wins":62},"google/gemini-3.8-flash":{"draws":13,"losses":30,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":2},"gpt-4.1":{"draws":6,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":10,"losses":7,"wins":7},"gpt-5.4":{"draws":32,"losses":51,"wins":17},"gpt-5.4-mini":{"draws":8,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":4,"wins":4},"gpt-5.5":{"draws":10,"losses":15,"wins":7},"gpt-5.6-luna":{"draws":38,"losses":24,"wins":42},"gpt-5.6-sol":{"draws":13,"losses":73,"wins":24},"gpt-5.6-terra":{"draws":16,"losses":12,"wins":22},"gpt-6-astra":{"draws":1,"losses":58,"wins":1},"gpt-6-luna":{"draws":0,"losses":0,"wins":2},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":19},"inclusionai/ling-3.0-flash":{"draws":10,"losses":13,"wins":15},"meituan/longcat-2.0":{"draws":14,"losses":17,"wins":37},"meta/muse-glimmer-30b":{"draws":20,"losses":4,"wins":22},"meta/muse-spark-1.2":{"draws":16,"losses":36,"wins":22},"meta/muse-spark-1.3":{"draws":7,"losses":21,"wins":10},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":4,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":37,"losses":46,"wins":29},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":3,"wins":13},"o3":{"draws":23,"losses":32,"wins":89},"openai/gpt-oss-120b":{"draws":10,"losses":5,"wins":27},"poolside/laguna-s-2.1":{"draws":37,"losses":6,"wins":33},"qwen/qwen3.7-max":{"draws":7,"losses":1,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":18,"wins":15},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":13},"qwen/qwen3.8-flash":{"draws":12,"losses":17,"wins":11},"qwen/qwen3.8-max":{"draws":19,"losses":28,"wins":15},"qwen/qwen3.8-max-0902":{"draws":0,"losses":3,"wins":1},"stealth/ox-alpha":{"draws":49,"losses":71,"wins":54},"stepfun/step-3.7-flash":{"draws":12,"losses":1,"wins":29},"tencent/hy3-preview":{"draws":5,"losses":4,"wins":5},"tencent/hy4-preview":{"draws":18,"losses":26,"wins":16},"thinkingmachines/inkling":{"draws":30,"losses":5,"wins":47},"thinkingmachines/inkling-small":{"draws":24,"losses":12,"wins":18},"x-ai/grok-4.5":{"draws":38,"losses":52,"wins":24},"x-ai/grok-4.6":{"draws":14,"losses":26,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":10,"losses":5,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":9,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":23,"losses":19,"wins":38},"z-ai/glm-5.3":{"draws":10,"losses":41,"wins":5},"z-ai/glm-5.3-flash":{"draws":11,"losses":24,"wins":15},"z-ai/glm-5.3-flashx":{"draws":1,"losses":1,"wins":0}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":8},"claude-fable-5":{"draws":1,"losses":2,"wins":3},"claude-fable-5-1":{"draws":0,"losses":11,"wins":5},"claude-opus-4-5":{"draws":7,"losses":11,"wins":58},"claude-opus-4-8":{"draws":2,"losses":5,"wins":21},"claude-opus-5":{"draws":28,"losses":65,"wins":41},"claude-opus-5-5":{"draws":0,"losses":1,"wins":3},"claude-sonnet-5":{"draws":3,"losses":2,"wins":9},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":3,"losses":1,"wins":22},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":1,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":23},"google/gemini-3.5-flash":{"draws":6,"losses":0,"wins":18},"google/gemini-3.5-flash-lite":{"draws":2,"losses":4,"wins":32},"google/gemini-3.6-flash":{"draws":3,"losses":21,"wins":22},"google/gemini-3.8-flash":{"draws":2,"losses":3,"wins":9},"google/gemma-4-31b-it":{"draws":5,"losses":4,"wins":9},"gpt-4.1":{"draws":0,"losses":0,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":10,"wins":37},"gpt-5.4":{"draws":2,"losses":5,"wins":5},"gpt-5.4-mini":{"draws":2,"losses":4,"wins":12},"gpt-5.4-nano":{"draws":7,"losses":1,"wins":34},"gpt-5.5":{"draws":11,"losses":23,"wins":20},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":13},"gpt-5.6-sol":{"draws":4,"losses":3,"wins":7},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":12},"gpt-6-astra":{"draws":4,"losses":11,"wins":1},"gpt-6-luna":{"draws":2,"losses":1,"wins":5},"gpt-6-sol":{"draws":1,"losses":0,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":14},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":7},"meta/muse-spark-1.2":{"draws":4,"losses":0,"wins":8},"meta/muse-spark-1.3":{"draws":1,"losses":2,"wins":7},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":21},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":1,"wins":9},"moonshotai/kimi-k3":{"draws":3,"losses":5,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":35},"o3":{"draws":0,"losses":10,"wins":46},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":14},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":17},"qwen/qwen3.7-plus":{"draws":0,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":6},"qwen/qwen3.8-flash":{"draws":2,"losses":1,"wins":5},"qwen/qwen3.8-max":{"draws":0,"losses":6,"wins":10},"qwen/qwen3.8-max-0902":{"draws":6,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":10,"losses":6,"wins":16},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":20},"tencent/hy3-preview":{"draws":6,"losses":8,"wins":20},"tencent/hy4-preview":{"draws":2,"losses":6,"wins":10},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":36},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":12},"x-ai/grok-4.5":{"draws":7,"losses":8,"wins":19},"x-ai/grok-4.6":{"draws":1,"losses":5,"wins":6},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.2":{"draws":7,"losses":10,"wins":41},"z-ai/glm-5.3":{"draws":5,"losses":5,"wins":8},"z-ai/glm-5.3-flash":{"draws":2,"losses":2,"wins":6},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":6}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":16},"claude-fable-5":{"draws":2,"losses":5,"wins":25},"claude-fable-5-1":{"draws":7,"losses":9,"wins":16},"claude-opus-4-5":{"draws":4,"losses":8,"wins":104},"claude-opus-4-8":{"draws":6,"losses":23,"wins":63},"claude-opus-5":{"draws":21,"losses":76,"wins":137},"claude-opus-5-5":{"draws":1,"losses":7,"wins":4},"claude-sonnet-5":{"draws":2,"losses":2,"wins":16},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":12},"deepseek/deepseek-v4-flash":{"draws":2,"losses":5,"wins":33},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":1,"wins":9},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":39},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":29},"google/gemini-3.5-flash-lite":{"draws":5,"losses":5,"wins":68},"google/gemini-3.6-flash":{"draws":7,"losses":12,"wins":65},"google/gemini-3.8-flash":{"draws":2,"losses":7,"wins":27},"google/gemma-4-31b-it":{"draws":0,"losses":5,"wins":15},"gpt-4.1":{"draws":1,"losses":1,"wins":18},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":7,"wins":45},"gpt-5.4":{"draws":0,"losses":1,"wins":11},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":20},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":35},"gpt-5.5":{"draws":4,"losses":13,"wins":45},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":25},"gpt-5.6-sol":{"draws":9,"losses":5,"wins":28},"gpt-5.6-terra":{"draws":2,"losses":1,"wins":21},"gpt-6-astra":{"draws":4,"losses":12,"wins":14},"gpt-6-luna":{"draws":2,"losses":0,"wins":8},"gpt-6-sol":{"draws":1,"losses":6,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":8},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":11},"meituan/longcat-2.0":{"draws":0,"losses":5,"wins":23},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":10},"meta/muse-spark-1.2":{"draws":0,"losses":3,"wins":11},"meta/muse-spark-1.3":{"draws":3,"losses":3,"wins":20},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":24},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":24},"moonshotai/kimi-k3":{"draws":4,"losses":7,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":48},"o3":{"draws":0,"losses":5,"wins":63},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":17},"poolside/laguna-s-2.1":{"draws":0,"losses":4,"wins":38},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":20},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":1,"wins":15},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":11},"qwen/qwen3.8-flash":{"draws":1,"losses":1,"wins":16},"qwen/qwen3.8-max":{"draws":1,"losses":1,"wins":18},"qwen/qwen3.8-max-0902":{"draws":3,"losses":3,"wins":4},"stealth/ox-alpha":{"draws":7,"losses":8,"wins":81},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":18},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":34},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":31},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":69},"thinkingmachines/inkling-small":{"draws":0,"losses":2,"wins":12},"x-ai/grok-4.5":{"draws":6,"losses":15,"wins":59},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":22},"x-ai/grok-4.7":{"draws":1,"losses":0,"wins":5},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":2,"losses":1,"wins":61},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":4,"losses":5,"wins":43},"z-ai/glm-5.3":{"draws":4,"losses":2,"wins":20},"z-ai/glm-5.3-flash":{"draws":5,"losses":3,"wins":24},"z-ai/glm-5.3-flashx":{"draws":0,"losses":1,"wins":7}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":4},"claude-fable-5":{"draws":1,"losses":1,"wins":6},"claude-fable-5-1":{"draws":2,"losses":2,"wins":6},"claude-opus-4-5":{"draws":0,"losses":0,"wins":14},"claude-opus-4-8":{"draws":0,"losses":0,"wins":10},"claude-opus-5":{"draws":1,"losses":0,"wins":11},"claude-opus-5-5":{"draws":3,"losses":7,"wins":26},"claude-sonnet-5":{"draws":0,"losses":0,"wins":4},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":14},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":12},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":12},"google/gemini-3.6-flash":{"draws":0,"losses":2,"wins":6},"google/gemini-3.8-flash":{"draws":0,"losses":1,"wins":9},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":0,"wins":4},"gpt-5.4":{"draws":0,"losses":2,"wins":8},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":6},"gpt-5.5":{"draws":0,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":1,"losses":0,"wins":11},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":4},"gpt-6-astra":{"draws":1,"losses":5,"wins":6},"gpt-6-luna":{"draws":1,"losses":0,"wins":45},"gpt-6-sol":{"draws":2,"losses":1,"wins":45},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":4},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":14},"meta/muse-spark-1.2":{"draws":0,"losses":2,"wins":4},"meta/muse-spark-1.3":{"draws":0,"losses":1,"wins":9},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":12},"o3":{"draws":0,"losses":0,"wins":8},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":12},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":10},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-max":{"draws":0,"losses":0,"wins":16},"qwen/qwen3.8-max-0902":{"draws":1,"losses":0,"wins":7},"stealth/ox-alpha":{"draws":1,"losses":0,"wins":35},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":10},"tencent/hy4-preview":{"draws":0,"losses":0,"wins":6},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":16},"x-ai/grok-4.6":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.7":{"draws":1,"losses":4,"wins":21},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":1,"wins":20},"z-ai/glm-5.2":{"draws":0,"losses":1,"wins":21},"z-ai/glm-5.3":{"draws":0,"losses":1,"wins":3},"z-ai/glm-5.3-flash":{"draws":1,"losses":0,"wins":9},"z-ai/glm-5.3-flashx":{"draws":2,"losses":1,"wins":35}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":4,"wins":19},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":1,"losses":55,"wins":2},"claude-opus-4-5":{"draws":31,"losses":31,"wins":32},"claude-opus-4-8":{"draws":3,"losses":6,"wins":5},"claude-opus-5":{"draws":4,"losses":28,"wins":6},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":18,"losses":9,"wins":41},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":3},"deepseek/deepseek-v4-flash":{"draws":17,"losses":8,"wins":23},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":15,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":9,"losses":15,"wins":20},"google/gemini-3.5-flash-lite":{"draws":28,"losses":24,"wins":100},"google/gemini-3.6-flash":{"draws":25,"losses":46,"wins":71},"google/gemini-3.8-flash":{"draws":13,"losses":18,"wins":19},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":3,"losses":2,"wins":3},"gpt-5.4":{"draws":23,"losses":41,"wins":26},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":4},"gpt-5.5":{"draws":2,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":26,"losses":27,"wins":33},"gpt-5.6-sol":{"draws":17,"losses":68,"wins":19},"gpt-5.6-terra":{"draws":10,"losses":15,"wins":23},"gpt-6-astra":{"draws":1,"losses":46,"wins":7},"gpt-6-luna":{"draws":1,"losses":0,"wins":1},"gpt-6-sol":{"draws":3,"losses":10,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":15},"inclusionai/ling-3.0-flash":{"draws":7,"losses":4,"wins":21},"meituan/longcat-2.0":{"draws":12,"losses":3,"wins":31},"meta/muse-glimmer-30b":{"draws":9,"losses":3,"wins":16},"meta/muse-spark-1.2":{"draws":20,"losses":11,"wins":39},"meta/muse-spark-1.3":{"draws":11,"losses":12,"wins":19},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":5},"mistralai/mistral-medium-3-5":{"draws":6,"losses":6,"wins":8},"moonshotai/kimi-k3":{"draws":24,"losses":32,"wins":28},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":6},"o3":{"draws":3,"losses":39,"wins":66},"openai/gpt-oss-120b":{"draws":11,"losses":6,"wins":19},"poolside/laguna-s-2.1":{"draws":15,"losses":0,"wins":33},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":14,"wins":14},"qwen/qwen3.8-27b":{"draws":10,"losses":5,"wins":13},"qwen/qwen3.8-flash":{"draws":5,"losses":6,"wins":13},"qwen/qwen3.8-max":{"draws":5,"losses":18,"wins":25},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":40,"losses":51,"wins":66},"stepfun/step-3.7-flash":{"draws":1,"losses":8,"wins":9},"tencent/hy3-preview":{"draws":5,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":9,"losses":14,"wins":19},"thinkingmachines/inkling":{"draws":16,"losses":10,"wins":34},"thinkingmachines/inkling-small":{"draws":18,"losses":6,"wins":34},"x-ai/grok-4.5":{"draws":27,"losses":27,"wins":16},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":16},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":5,"losses":0,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":9,"losses":13,"wins":24},"z-ai/glm-5.3":{"draws":9,"losses":33,"wins":10},"z-ai/glm-5.3-flash":{"draws":6,"losses":34,"wins":14},"z-ai/glm-5.3-flashx":{"draws":5,"losses":1,"wins":6}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":5,"wins":7},"claude-fable-5":{"draws":8,"losses":22,"wins":6},"claude-fable-5-1":{"draws":4,"losses":31,"wins":1},"claude-opus-4-5":{"draws":5,"losses":16,"wins":13},"claude-opus-4-8":{"draws":4,"losses":5,"wins":1},"claude-opus-5":{"draws":3,"losses":10,"wins":3},"claude-opus-5-5":{"draws":0,"losses":5,"wins":1},"claude-sonnet-5":{"draws":23,"losses":17,"wins":8},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":1},"deepseek/deepseek-v4-flash":{"draws":8,"losses":13,"wins":19},"deepseek/deepseek-v4-pro":{"draws":23,"losses":18,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":12,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":10,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":18,"losses":11,"wins":13},"google/gemini-3.5-flash-lite":{"draws":32,"losses":30,"wins":20},"google/gemini-3.6-flash":{"draws":21,"losses":29,"wins":12},"google/gemini-3.8-flash":{"draws":10,"losses":16,"wins":10},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":4},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":2,"wins":2},"gpt-5.4":{"draws":17,"losses":12,"wins":13},"gpt-5.4-mini":{"draws":0,"losses":4,"wins":0},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":4},"gpt-5.5":{"draws":1,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":30,"losses":6,"wins":14},"gpt-5.6-sol":{"draws":5,"losses":22,"wins":7},"gpt-5.6-terra":{"draws":17,"losses":10,"wins":11},"gpt-6-astra":{"draws":1,"losses":24,"wins":1},"gpt-6-luna":{"draws":3,"losses":2,"wins":1},"gpt-6-sol":{"draws":1,"losses":8,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":21,"losses":4,"wins":9},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":6},"meituan/longcat-2.0":{"draws":14,"losses":2,"wins":10},"meta/muse-glimmer-30b":{"draws":29,"losses":5,"wins":6},"meta/muse-spark-1.2":{"draws":10,"losses":12,"wins":4},"meta/muse-spark-1.3":{"draws":10,"losses":15,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":18,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":11,"losses":11,"wins":14},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":0},"o3":{"draws":10,"losses":17,"wins":11},"openai/gpt-oss-120b":{"draws":23,"losses":15,"wins":4},"poolside/laguna-s-2.1":{"draws":14,"losses":6,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":14,"wins":13},"qwen/qwen3.8-27b":{"draws":6,"losses":10,"wins":8},"qwen/qwen3.8-flash":{"draws":12,"losses":10,"wins":6},"qwen/qwen3.8-max":{"draws":16,"losses":19,"wins":7},"qwen/qwen3.8-max-0902":{"draws":0,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":47,"losses":48,"wins":33},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":13,"losses":17,"wins":10},"thinkingmachines/inkling":{"draws":21,"losses":6,"wins":7},"thinkingmachines/inkling-small":{"draws":24,"losses":7,"wins":11},"x-ai/grok-4.5":{"draws":7,"losses":9,"wins":6},"x-ai/grok-4.6":{"draws":13,"losses":26,"wins":5},"x-ai/grok-4.7":{"draws":1,"losses":5,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":10,"losses":7,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":1},"z-ai/glm-5.2":{"draws":23,"losses":16,"wins":9},"z-ai/glm-5.3":{"draws":11,"losses":21,"wins":4},"z-ai/glm-5.3-flash":{"draws":11,"losses":13,"wins":8},"z-ai/glm-5.3-flashx":{"draws":1,"losses":2,"wins":1}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":10,"wins":19},"claude-fable-5":{"draws":9,"losses":27,"wins":12},"claude-fable-5-1":{"draws":3,"losses":50,"wins":1},"claude-opus-4-5":{"draws":13,"losses":11,"wins":18},"claude-opus-4-8":{"draws":2,"losses":7,"wins":9},"claude-opus-5":{"draws":4,"losses":17,"wins":1},"claude-opus-5-5":{"draws":1,"losses":9,"wins":0},"claude-sonnet-5":{"draws":17,"losses":17,"wins":8},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":21,"losses":11,"wins":22},"deepseek/deepseek-v4-pro":{"draws":12,"losses":6,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":18,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":1},"google/gemini-3.5-flash":{"draws":14,"losses":14,"wins":24},"google/gemini-3.5-flash-lite":{"draws":32,"losses":20,"wins":34},"google/gemini-3.6-flash":{"draws":18,"losses":33,"wins":29},"google/gemini-3.8-flash":{"draws":22,"losses":22,"wins":8},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":1,"losses":0,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":13,"losses":2,"wins":5},"gpt-5.4":{"draws":26,"losses":16,"wins":8},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":3},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":11},"gpt-5.5":{"draws":4,"losses":8,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":5,"wins":17},"gpt-5.6-sol":{"draws":6,"losses":25,"wins":17},"gpt-5.6-terra":{"draws":19,"losses":13,"wins":10},"gpt-6-astra":{"draws":4,"losses":43,"wins":3},"gpt-6-luna":{"draws":3,"losses":8,"wins":1},"gpt-6-sol":{"draws":1,"losses":3,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":8},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":7,"losses":5,"wins":14},"meta/muse-glimmer-30b":{"draws":19,"losses":9,"wins":20},"meta/muse-spark-1.2":{"draws":8,"losses":17,"wins":11},"meta/muse-spark-1.3":{"draws":14,"losses":19,"wins":11},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":2},"mistralai/mistral-medium-3-5":{"draws":10,"losses":0,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":14,"losses":9,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":2},"o3":{"draws":14,"losses":14,"wins":30},"openai/gpt-oss-120b":{"draws":18,"losses":7,"wins":11},"poolside/laguna-s-2.1":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":17,"wins":15},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":9},"qwen/qwen3.8-flash":{"draws":10,"losses":12,"wins":8},"qwen/qwen3.8-max":{"draws":12,"losses":19,"wins":13},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":57,"losses":68,"wins":49},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":12},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":1},"tencent/hy4-preview":{"draws":15,"losses":21,"wins":14},"thinkingmachines/inkling":{"draws":13,"losses":3,"wins":18},"thinkingmachines/inkling-small":{"draws":23,"losses":0,"wins":27},"x-ai/grok-4.5":{"draws":9,"losses":10,"wins":21},"x-ai/grok-4.6":{"draws":17,"losses":19,"wins":10},"x-ai/grok-4.7":{"draws":0,"losses":7,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":22,"losses":30,"wins":18},"z-ai/glm-5.3":{"draws":10,"losses":24,"wins":8},"z-ai/glm-5.3-flash":{"draws":23,"losses":19,"wins":14}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":5,"wins":26},"claude-fable-5":{"draws":14,"losses":25,"wins":11},"claude-fable-5-1":{"draws":4,"losses":51,"wins":1},"claude-opus-4-5":{"draws":8,"losses":9,"wins":29},"claude-opus-4-8":{"draws":4,"losses":2,"wins":4},"claude-opus-5":{"draws":3,"losses":20,"wins":5},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":17,"losses":10,"wins":29},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":19,"losses":5,"wins":24},"deepseek/deepseek-v4-pro":{"draws":14,"losses":14,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":6,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":18,"losses":16,"wins":22},"google/gemini-3.5-flash-lite":{"draws":31,"losses":8,"wins":39},"google/gemini-3.6-flash":{"draws":22,"losses":35,"wins":37},"google/gemini-3.8-flash":{"draws":10,"losses":18,"wins":26},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":10,"losses":6,"wins":16},"gpt-5.4":{"draws":16,"losses":11,"wins":15},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":5},"gpt-5.5":{"draws":0,"losses":1,"wins":3},"gpt-5.6-luna":{"draws":15,"losses":7,"wins":20},"gpt-5.6-sol":{"draws":7,"losses":26,"wins":17},"gpt-5.6-terra":{"draws":16,"losses":7,"wins":21},"gpt-6-astra":{"draws":5,"losses":39,"wins":0},"gpt-6-luna":{"draws":0,"losses":2,"wins":2},"gpt-6-sol":{"draws":0,"losses":6,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":15,"losses":2,"wins":17},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":11,"losses":7,"wins":18},"meta/muse-glimmer-30b":{"draws":15,"losses":4,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":11,"wins":14},"meta/muse-spark-1.3":{"draws":15,"losses":17,"wins":18},"minimax/minimax-m3":{"draws":1,"losses":2,"wins":7},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":16,"losses":2,"wins":18},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":7},"o3":{"draws":11,"losses":5,"wins":24},"openai/gpt-oss-120b":{"draws":19,"losses":3,"wins":12},"poolside/laguna-s-2.1":{"draws":12,"losses":4,"wins":14},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":16,"wins":23},"qwen/qwen3.8-27b":{"draws":9,"losses":13,"wins":12},"qwen/qwen3.8-flash":{"draws":14,"losses":11,"wins":13},"qwen/qwen3.8-max":{"draws":12,"losses":13,"wins":21},"qwen/qwen3.8-max-0902":{"draws":5,"losses":1,"wins":0},"stealth/ox-alpha":{"draws":41,"losses":50,"wins":73},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":7,"losses":18,"wins":23},"thinkingmachines/inkling":{"draws":9,"losses":10,"wins":15},"thinkingmachines/inkling-small":{"draws":16,"losses":7,"wins":21},"x-ai/grok-4.5":{"draws":8,"losses":5,"wins":9},"x-ai/grok-4.6":{"draws":17,"losses":18,"wins":15},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":10,"losses":3,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":1},"z-ai/glm-5.2":{"draws":13,"losses":22,"wins":27},"z-ai/glm-5.3":{"draws":9,"losses":23,"wins":14},"z-ai/glm-5.3-flash":{"draws":13,"losses":29,"wins":16},"z-ai/glm-5.3-flashx":{"draws":1,"losses":6,"wins":1}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":0,"wins":3},"claude-fable-5":{"draws":1,"losses":1,"wins":8},"claude-fable-5-1":{"draws":2,"losses":11,"wins":1},"claude-opus-4-5":{"draws":2,"losses":0,"wins":22},"claude-opus-4-8":{"draws":1,"losses":1,"wins":4},"claude-opus-5":{"draws":5,"losses":7,"wins":4},"claude-opus-5-5":{"draws":0,"losses":13,"wins":1},"claude-sonnet-5":{"draws":6,"losses":1,"wins":7},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":21},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":8,"wins":17},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":7},"google/gemini-3.5-flash":{"draws":1,"losses":2,"wins":3},"google/gemini-3.5-flash-lite":{"draws":0,"losses":2,"wins":12},"google/gemini-3.6-flash":{"draws":7,"losses":6,"wins":17},"google/gemini-3.8-flash":{"draws":1,"losses":0,"wins":5},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-4.1":{"draws":3,"losses":0,"wins":7},"gpt-5":{"draws":3,"losses":0,"wins":3},"gpt-5.4":{"draws":4,"losses":3,"wins":3},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":5},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":8},"gpt-5.5":{"draws":2,"losses":0,"wins":4},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":8},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":0,"wins":5},"gpt-6-astra":{"draws":1,"losses":8,"wins":1},"gpt-6-luna":{"draws":5,"losses":3,"wins":8},"gpt-6-sol":{"draws":6,"losses":5,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":3},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":10},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":10},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":2,"losses":1,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":2,"losses":2,"wins":8},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":10},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.8-flash":{"draws":1,"losses":1,"wins":8},"qwen/qwen3.8-max":{"draws":3,"losses":1,"wins":8},"qwen/qwen3.8-max-0902":{"draws":5,"losses":5,"wins":12},"stealth/ox-alpha":{"draws":5,"losses":10,"wins":13},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":7},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":8},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.6":{"draws":4,"losses":2,"wins":4},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":1},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":13},"z-ai/glm-5.3":{"draws":5,"losses":3,"wins":2},"z-ai/glm-5.3-flash":{"draws":1,"losses":1,"wins":4},"z-ai/glm-5.3-flashx":{"draws":3,"losses":4,"wins":5}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":6,"wins":2},"claude-fable-5":{"draws":1,"losses":4,"wins":1},"claude-fable-5-1":{"draws":2,"losses":8,"wins":0},"claude-opus-4-5":{"draws":11,"losses":33,"wins":4},"claude-opus-4-8":{"draws":11,"losses":29,"wins":2},"claude-opus-5":{"draws":6,"losses":38,"wins":0},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":8,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":11,"losses":17,"wins":14},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":4,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":8,"wins":10},"google/gemini-3.5-flash":{"draws":7,"losses":9,"wins":2},"google/gemini-3.5-flash-lite":{"draws":13,"losses":17,"wins":8},"google/gemini-3.6-flash":{"draws":4,"losses":23,"wins":1},"google/gemini-3.8-flash":{"draws":1,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":13,"losses":11,"wins":4},"gpt-4.1":{"draws":4,"losses":4,"wins":4},"gpt-5":{"draws":10,"losses":16,"wins":0},"gpt-5.4":{"draws":3,"losses":9,"wins":0},"gpt-5.4-mini":{"draws":5,"losses":7,"wins":4},"gpt-5.4-nano":{"draws":4,"losses":29,"wins":7},"gpt-5.5":{"draws":7,"losses":16,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":8,"wins":2},"gpt-5.6-terra":{"draws":3,"losses":11,"wins":2},"gpt-6-astra":{"draws":0,"losses":10,"wins":0},"gpt-6-luna":{"draws":0,"losses":7,"wins":1},"gpt-6-sol":{"draws":1,"losses":7,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":10,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":7},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":2},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":4,"losses":4,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":2},"moonshotai/kimi-k3":{"draws":2,"losses":7,"wins":1},"nex-agi/nex-n2-pro":{"draws":0,"losses":12,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":8,"wins":3},"o3":{"draws":6,"losses":29,"wins":3},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":5},"qwen/qwen3.7-max":{"draws":0,"losses":10,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":6,"wins":0},"qwen/qwen3.8-27b":{"draws":3,"losses":8,"wins":3},"qwen/qwen3.8-flash":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":2,"losses":12,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":3},"tencent/hy3-preview":{"draws":9,"losses":9,"wins":8},"tencent/hy4-preview":{"draws":2,"losses":6,"wins":0},"thinkingmachines/inkling":{"draws":11,"losses":18,"wins":7},"thinkingmachines/inkling-small":{"draws":2,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":2,"losses":10,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":8,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":7,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":27,"losses":14,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":12,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":12,"wins":7},"z-ai/glm-5.3":{"draws":1,"losses":8,"wins":1},"z-ai/glm-5.3-flash":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.3-flashx":{"draws":0,"losses":6,"wins":0}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":3,"wins":19},"claude-fable-5":{"draws":6,"losses":40,"wins":14},"claude-fable-5-1":{"draws":5,"losses":61,"wins":10},"claude-opus-4-5":{"draws":12,"losses":9,"wins":35},"claude-opus-4-8":{"draws":11,"losses":8,"wins":5},"claude-opus-5":{"draws":6,"losses":24,"wins":4},"claude-opus-5-5":{"draws":0,"losses":8,"wins":2},"claude-sonnet-5":{"draws":12,"losses":9,"wins":17},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":6},"deepseek/deepseek-v4-flash":{"draws":10,"losses":6,"wins":26},"deepseek/deepseek-v4-pro":{"draws":7,"losses":17,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":8,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":7,"losses":3,"wins":22},"google/gemini-3.5-flash-lite":{"draws":18,"losses":8,"wins":48},"google/gemini-3.6-flash":{"draws":12,"losses":19,"wins":41},"google/gemini-3.8-flash":{"draws":8,"losses":17,"wins":25},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":1,"losses":1,"wins":8},"gpt-5":{"draws":5,"losses":1,"wins":6},"gpt-5.4":{"draws":9,"losses":19,"wins":22},"gpt-5.4-mini":{"draws":1,"losses":2,"wins":5},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":16},"gpt-5.5":{"draws":5,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":19},"gpt-5.6-sol":{"draws":8,"losses":28,"wins":22},"gpt-5.6-terra":{"draws":19,"losses":14,"wins":17},"gpt-6-astra":{"draws":10,"losses":47,"wins":3},"gpt-6-luna":{"draws":3,"losses":0,"wins":7},"gpt-6-sol":{"draws":2,"losses":5,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":4,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":3,"losses":1,"wins":8},"meituan/longcat-2.0":{"draws":11,"losses":2,"wins":29},"meta/muse-glimmer-30b":{"draws":3,"losses":4,"wins":21},"meta/muse-spark-1.2":{"draws":6,"losses":13,"wins":19},"meta/muse-spark-1.3":{"draws":6,"losses":25,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":14},"moonshotai/kimi-k3":{"draws":15,"losses":12,"wins":19},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":1},"o3":{"draws":4,"losses":11,"wins":35},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":21},"poolside/laguna-s-2.1":{"draws":8,"losses":2,"wins":22},"qwen/qwen3.7-max":{"draws":6,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":16,"wins":25},"qwen/qwen3.8-27b":{"draws":5,"losses":12,"wins":9},"qwen/qwen3.8-flash":{"draws":8,"losses":8,"wins":18},"qwen/qwen3.8-max":{"draws":20,"losses":10,"wins":20},"qwen/qwen3.8-max-0902":{"draws":0,"losses":4,"wins":4},"stealth/ox-alpha":{"draws":46,"losses":58,"wins":84},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":9,"losses":27,"wins":20},"thinkingmachines/inkling":{"draws":10,"losses":3,"wins":21},"thinkingmachines/inkling-small":{"draws":4,"losses":7,"wins":21},"x-ai/grok-4.5":{"draws":10,"losses":10,"wins":14},"x-ai/grok-4.6":{"draws":15,"losses":26,"wins":19},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":7},"xiaomi/mimo-v2.5":{"draws":6,"losses":0,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":2},"z-ai/glm-5.2":{"draws":7,"losses":21,"wins":24},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":12},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":29},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":2}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":28,"losses":25,"wins":25},"claude-fable-5":{"draws":11,"losses":36,"wins":11},"claude-fable-5-1":{"draws":7,"losses":61,"wins":0},"claude-opus-4-5":{"draws":42,"losses":68,"wins":50},"claude-opus-4-8":{"draws":5,"losses":23,"wins":6},"claude-opus-5":{"draws":7,"losses":59,"wins":4},"claude-opus-5-5":{"draws":2,"losses":14,"wins":0},"claude-sonnet-5":{"draws":43,"losses":71,"wins":46},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":28,"losses":29,"wins":29},"deepseek/deepseek-v4-pro":{"draws":19,"losses":40,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":31,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":4,"wins":7},"google/gemini-3.1-flash-lite":{"draws":8,"losses":7,"wins":9},"google/gemini-3.5-flash":{"draws":25,"losses":40,"wins":27},"google/gemini-3.5-flash-lite":{"draws":88,"losses":118,"wins":124},"google/gemini-3.6-flash":{"draws":72,"losses":158,"wins":74},"google/gemini-3.8-flash":{"draws":10,"losses":42,"wins":6},"google/gemma-4-31b-it":{"draws":7,"losses":4,"wins":5},"gpt-4.1":{"draws":0,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":3,"losses":3,"wins":0},"gpt-5":{"draws":10,"losses":12,"wins":4},"gpt-5.4":{"draws":29,"losses":80,"wins":35},"gpt-5.4-mini":{"draws":4,"losses":10,"wins":10},"gpt-5.4-nano":{"draws":3,"losses":10,"wins":15},"gpt-5.5":{"draws":10,"losses":14,"wins":4},"gpt-5.6-luna":{"draws":47,"losses":53,"wins":62},"gpt-5.6-sol":{"draws":26,"losses":112,"wins":10},"gpt-5.6-terra":{"draws":21,"losses":33,"wins":16},"gpt-6-astra":{"draws":8,"losses":39,"wins":1},"gpt-6-luna":{"draws":0,"losses":6,"wins":2},"gpt-6-sol":{"draws":1,"losses":12,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":26,"losses":9,"wins":33},"inclusionai/ling-3.0-flash":{"draws":14,"losses":18,"wins":28},"meituan/longcat-2.0":{"draws":25,"losses":37,"wins":59},"meta/muse-glimmer-30b":{"draws":22,"losses":21,"wins":33},"meta/muse-spark-1.2":{"draws":25,"losses":53,"wins":30},"meta/muse-spark-1.3":{"draws":13,"losses":34,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":14,"losses":10,"wins":32},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":50,"losses":78,"wins":46},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":14,"wins":12},"o3":{"draws":17,"losses":124,"wins":91},"openai/gpt-oss-120b":{"draws":26,"losses":18,"wins":32},"poolside/laguna-s-2.1":{"draws":55,"losses":35,"wins":38},"qwen/qwen3.7-max":{"draws":6,"losses":3,"wins":5},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":25,"losses":38,"wins":19},"qwen/qwen3.8-27b":{"draws":5,"losses":21,"wins":10},"qwen/qwen3.8-flash":{"draws":19,"losses":18,"wins":9},"qwen/qwen3.8-max":{"draws":25,"losses":34,"wins":15},"qwen/qwen3.8-max-0902":{"draws":3,"losses":3,"wins":2},"stealth/ox-alpha":{"draws":49,"losses":127,"wins":74},"stepfun/step-3.7-flash":{"draws":10,"losses":26,"wins":20},"tencent/hy3-preview":{"draws":7,"losses":10,"wins":5},"tencent/hy4-preview":{"draws":23,"losses":36,"wins":19},"thinkingmachines/inkling":{"draws":52,"losses":34,"wins":72},"thinkingmachines/inkling-small":{"draws":23,"losses":39,"wins":23},"x-ai/grok-4.5":{"draws":32,"losses":65,"wins":35},"x-ai/grok-4.6":{"draws":16,"losses":40,"wins":12},"x-ai/grok-4.7":{"draws":0,"losses":10,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":6},"xiaomi/mimo-v2.5":{"draws":10,"losses":8,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":6,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":34,"losses":33,"wins":49},"z-ai/glm-5.3":{"draws":14,"losses":50,"wins":6},"z-ai/glm-5.3-flash":{"draws":16,"losses":34,"wins":10},"z-ai/glm-5.3-flashx":{"draws":3,"losses":10,"wins":3}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":8,"wins":24},"claude-fable-5":{"draws":5,"losses":31,"wins":32},"claude-fable-5-1":{"draws":6,"losses":60,"wins":14},"claude-opus-4-5":{"draws":28,"losses":41,"wins":85},"claude-opus-4-8":{"draws":5,"losses":16,"wins":17},"claude-opus-5":{"draws":20,"losses":67,"wins":17},"claude-opus-5-5":{"draws":2,"losses":10,"wins":0},"claude-sonnet-5":{"draws":14,"losses":31,"wins":89},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":10,"losses":3,"wins":55},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":12,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":9,"wins":8},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":16},"google/gemini-3.5-flash":{"draws":12,"losses":29,"wins":33},"google/gemini-3.5-flash-lite":{"draws":72,"losses":36,"wins":184},"google/gemini-3.6-flash":{"draws":37,"losses":81,"wins":132},"google/gemini-3.8-flash":{"draws":9,"losses":28,"wins":39},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":6},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":4,"losses":20,"wins":20},"gpt-5.4":{"draws":22,"losses":62,"wins":56},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":17},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":4},"gpt-5.5":{"draws":8,"losses":15,"wins":17},"gpt-5.6-luna":{"draws":23,"losses":36,"wins":63},"gpt-5.6-sol":{"draws":12,"losses":57,"wins":69},"gpt-5.6-terra":{"draws":9,"losses":11,"wins":34},"gpt-6-astra":{"draws":6,"losses":46,"wins":10},"gpt-6-luna":{"draws":9,"losses":3,"wins":14},"gpt-6-sol":{"draws":1,"losses":12,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":17},"inclusionai/ling-3.0-flash":{"draws":20,"losses":4,"wins":28},"meituan/longcat-2.0":{"draws":21,"losses":15,"wins":71},"meta/muse-glimmer-30b":{"draws":19,"losses":3,"wins":32},"meta/muse-spark-1.2":{"draws":14,"losses":37,"wins":53},"meta/muse-spark-1.3":{"draws":1,"losses":26,"wins":31},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":29,"losses":26,"wins":111},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":29},"o3":{"draws":32,"losses":39,"wins":133},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":26},"poolside/laguna-s-2.1":{"draws":30,"losses":3,"wins":53},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":24,"wins":50},"qwen/qwen3.8-27b":{"draws":16,"losses":5,"wins":19},"qwen/qwen3.8-flash":{"draws":17,"losses":7,"wins":26},"qwen/qwen3.8-max":{"draws":16,"losses":19,"wins":38},"qwen/qwen3.8-max-0902":{"draws":1,"losses":5,"wins":6},"stealth/ox-alpha":{"draws":40,"losses":65,"wins":119},"stepfun/step-3.7-flash":{"draws":12,"losses":1,"wins":36},"tencent/hy3-preview":{"draws":5,"losses":9,"wins":16},"tencent/hy4-preview":{"draws":10,"losses":20,"wins":46},"thinkingmachines/inkling":{"draws":33,"losses":20,"wins":69},"thinkingmachines/inkling-small":{"draws":15,"losses":7,"wins":28},"x-ai/grok-4.5":{"draws":14,"losses":40,"wins":74},"x-ai/grok-4.6":{"draws":11,"losses":27,"wins":34},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":8,"losses":4,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":15,"losses":15,"wins":50},"z-ai/glm-5.3":{"draws":6,"losses":45,"wins":23},"z-ai/glm-5.3-flash":{"draws":20,"losses":27,"wins":27},"z-ai/glm-5.3-flashx":{"draws":1,"losses":0,"wins":9}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":5,"wins":24},"claude-fable-5":{"draws":6,"losses":25,"wins":21},"claude-fable-5-1":{"draws":8,"losses":44,"wins":8},"claude-opus-4-5":{"draws":7,"losses":10,"wins":29},"claude-opus-4-8":{"draws":1,"losses":4,"wins":3},"claude-opus-5":{"draws":2,"losses":39,"wins":11},"claude-opus-5-5":{"draws":1,"losses":4,"wins":1},"claude-sonnet-5":{"draws":6,"losses":14,"wins":34},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":4,"losses":4,"wins":32},"deepseek/deepseek-v4-pro":{"draws":13,"losses":7,"wins":28},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":14,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":5,"wins":3},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.5-flash":{"draws":12,"losses":7,"wins":35},"google/gemini-3.5-flash-lite":{"draws":9,"losses":2,"wins":57},"google/gemini-3.6-flash":{"draws":6,"losses":21,"wins":39},"google/gemini-3.8-flash":{"draws":5,"losses":13,"wins":12},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":3},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":3,"wins":12},"gpt-5.4":{"draws":13,"losses":23,"wins":22},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":8},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":8},"gpt-5.5":{"draws":0,"losses":8,"wins":4},"gpt-5.6-luna":{"draws":5,"losses":8,"wins":21},"gpt-5.6-sol":{"draws":4,"losses":26,"wins":28},"gpt-5.6-terra":{"draws":10,"losses":13,"wins":15},"gpt-6-astra":{"draws":7,"losses":46,"wins":5},"gpt-6-luna":{"draws":2,"losses":1,"wins":5},"gpt-6-sol":{"draws":0,"losses":0,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":1,"wins":13},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":23},"meta/muse-glimmer-30b":{"draws":3,"losses":6,"wins":17},"meta/muse-spark-1.2":{"draws":2,"losses":12,"wins":18},"meta/muse-spark-1.3":{"draws":3,"losses":22,"wins":15},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":7},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":11,"losses":12,"wins":25},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":3,"losses":8,"wins":35},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":30},"poolside/laguna-s-2.1":{"draws":3,"losses":1,"wins":18},"qwen/qwen3.7-max":{"draws":3,"losses":7,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":18,"wins":24},"qwen/qwen3.8-27b":{"draws":4,"losses":15,"wins":13},"qwen/qwen3.8-flash":{"draws":4,"losses":7,"wins":17},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":20},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":2},"stealth/ox-alpha":{"draws":24,"losses":48,"wins":85},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":8},"tencent/hy4-preview":{"draws":3,"losses":16,"wins":15},"thinkingmachines/inkling":{"draws":6,"losses":2,"wins":18},"thinkingmachines/inkling-small":{"draws":12,"losses":6,"wins":16},"x-ai/grok-4.5":{"draws":7,"losses":19,"wins":16},"x-ai/grok-4.6":{"draws":9,"losses":19,"wins":22},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":8,"losses":5,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":13,"losses":15,"wins":34},"z-ai/glm-5.3":{"draws":8,"losses":35,"wins":19},"z-ai/glm-5.3-flash":{"draws":15,"losses":14,"wins":27},"z-ai/glm-5.3-flashx":{"draws":0,"losses":2,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":2,"wins":6},"claude-fable-5":{"draws":5,"losses":6,"wins":5},"claude-fable-5-1":{"draws":0,"losses":13,"wins":1},"claude-opus-4-5":{"draws":28,"losses":12,"wins":16},"claude-opus-4-8":{"draws":13,"losses":31,"wins":8},"claude-opus-5":{"draws":7,"losses":78,"wins":7},"claude-opus-5-5":{"draws":0,"losses":6,"wins":2},"claude-sonnet-5":{"draws":10,"losses":5,"wins":7},"cohere/north-mini-code":{"draws":6,"losses":6,"wins":6},"deepseek/deepseek-v4-flash":{"draws":14,"losses":1,"wins":23},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":6,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":14,"losses":2,"wins":22},"google/gemini-3.5-flash":{"draws":4,"losses":6,"wins":8},"google/gemini-3.5-flash-lite":{"draws":18,"losses":9,"wins":13},"google/gemini-3.6-flash":{"draws":18,"losses":24,"wins":16},"google/gemini-3.8-flash":{"draws":2,"losses":8,"wins":10},"google/gemma-4-31b-it":{"draws":6,"losses":1,"wins":11},"gpt-4.1":{"draws":5,"losses":7,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":10,"losses":1,"wins":15},"gpt-5.4":{"draws":1,"losses":10,"wins":3},"gpt-5.4-mini":{"draws":6,"losses":7,"wins":5},"gpt-5.4-nano":{"draws":7,"losses":14,"wins":23},"gpt-5.5":{"draws":18,"losses":19,"wins":11},"gpt-5.6-luna":{"draws":1,"losses":4,"wins":5},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":5,"wins":4},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"gpt-6-luna":{"draws":2,"losses":3,"wins":5},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":5,"losses":2,"wins":7},"inclusionai/ling-3.0-flash":{"draws":5,"losses":6,"wins":13},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":7},"meta/muse-glimmer-30b":{"draws":6,"losses":1,"wins":5},"meta/muse-spark-1.2":{"draws":6,"losses":2,"wins":6},"meta/muse-spark-1.3":{"draws":5,"losses":5,"wins":4},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":15},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":5,"losses":9,"wins":8},"nex-agi/nex-n2-pro":{"draws":11,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":25,"losses":1,"wins":24},"o3":{"draws":13,"losses":18,"wins":27},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":9,"losses":13,"wins":6},"qwen/qwen3.7-max":{"draws":12,"losses":2,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":2,"wins":5},"qwen/qwen3.8-27b":{"draws":0,"losses":4,"wins":8},"qwen/qwen3.8-flash":{"draws":1,"losses":1,"wins":6},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.8-max-0902":{"draws":8,"losses":1,"wins":3},"stealth/ox-alpha":{"draws":15,"losses":22,"wins":9},"stepfun/step-3.7-flash":{"draws":8,"losses":0,"wins":16},"tencent/hy3-preview":{"draws":17,"losses":10,"wins":15},"tencent/hy4-preview":{"draws":7,"losses":0,"wins":1},"thinkingmachines/inkling":{"draws":17,"losses":10,"wins":21},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":6},"x-ai/grok-4.5":{"draws":8,"losses":17,"wins":7},"x-ai/grok-4.6":{"draws":5,"losses":4,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":38,"losses":7,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":9,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":28,"losses":19,"wins":19},"z-ai/glm-5.3":{"draws":0,"losses":10,"wins":2},"z-ai/glm-5.3-flash":{"draws":6,"losses":6,"wins":2},"z-ai/glm-5.3-flashx":{"draws":5,"losses":1,"wins":2}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":4,"wins":11},"claude-fable-5":{"draws":13,"losses":14,"wins":23},"claude-fable-5-1":{"draws":8,"losses":36,"wins":12},"claude-opus-4-5":{"draws":10,"losses":7,"wins":49},"claude-opus-4-8":{"draws":2,"losses":5,"wins":7},"claude-opus-5":{"draws":1,"losses":14,"wins":3},"claude-opus-5-5":{"draws":0,"losses":7,"wins":3},"claude-sonnet-5":{"draws":13,"losses":14,"wins":63},"deepseek/deepseek-v4-flash":{"draws":8,"losses":6,"wins":26},"deepseek/deepseek-v4-pro":{"draws":11,"losses":6,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":6,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":14},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":4,"losses":8,"wins":30},"google/gemini-3.5-flash-lite":{"draws":16,"losses":12,"wins":110},"google/gemini-3.6-flash":{"draws":24,"losses":24,"wins":88},"google/gemini-3.8-flash":{"draws":3,"losses":14,"wins":29},"google/gemma-4-31b-it":{"draws":3,"losses":3,"wins":6},"gpt-4.1":{"draws":2,"losses":0,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":12,"losses":4,"wins":51},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":9},"gpt-5.4-nano":{"draws":0,"losses":6,"wins":12},"gpt-5.5":{"draws":5,"losses":0,"wins":5},"gpt-5.6-luna":{"draws":11,"losses":3,"wins":63},"gpt-5.6-sol":{"draws":23,"losses":34,"wins":47},"gpt-5.6-terra":{"draws":4,"losses":5,"wins":31},"gpt-6-astra":{"draws":6,"losses":38,"wins":6},"gpt-6-luna":{"draws":3,"losses":0,"wins":3},"gpt-6-sol":{"draws":0,"losses":3,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":14},"meituan/longcat-2.0":{"draws":6,"losses":0,"wins":33},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":14},"meta/muse-spark-1.2":{"draws":5,"losses":14,"wins":47},"meta/muse-spark-1.3":{"draws":4,"losses":13,"wins":25},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":5},"moonshotai/kimi-k3":{"draws":9,"losses":15,"wins":56},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":6},"o3":{"draws":0,"losses":9,"wins":79},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":21},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":12,"wins":22},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":14},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":11},"qwen/qwen3.8-max":{"draws":6,"losses":11,"wins":25},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":12},"stealth/ox-alpha":{"draws":44,"losses":28,"wins":81},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":15},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":1},"tencent/hy4-preview":{"draws":7,"losses":10,"wins":25},"thinkingmachines/inkling":{"draws":11,"losses":10,"wins":27},"thinkingmachines/inkling-small":{"draws":5,"losses":3,"wins":6},"x-ai/grok-4.5":{"draws":8,"losses":11,"wins":40},"x-ai/grok-4.6":{"draws":9,"losses":12,"wins":33},"x-ai/grok-4.7":{"draws":2,"losses":3,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":6},"z-ai/glm-5.2":{"draws":12,"losses":9,"wins":25},"z-ai/glm-5.3":{"draws":2,"losses":25,"wins":27},"z-ai/glm-5.3-flash":{"draws":5,"losses":8,"wins":23},"z-ai/glm-5.3-flashx":{"draws":0,"losses":0,"wins":6}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":2,"wins":8},"claude-fable-5":{"draws":4,"losses":5,"wins":3},"claude-fable-5-1":{"draws":0,"losses":13,"wins":3},"claude-opus-4-5":{"draws":15,"losses":6,"wins":37},"claude-opus-4-8":{"draws":5,"losses":9,"wins":34},"claude-opus-5":{"draws":4,"losses":57,"wins":61},"claude-opus-5-5":{"draws":0,"losses":4,"wins":4},"claude-sonnet-5":{"draws":0,"losses":1,"wins":11},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":8},"deepseek/deepseek-v4-flash":{"draws":10,"losses":0,"wins":12},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":1,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":14},"google/gemini-3.5-flash":{"draws":8,"losses":3,"wins":7},"google/gemini-3.5-flash-lite":{"draws":10,"losses":5,"wins":15},"google/gemini-3.6-flash":{"draws":12,"losses":14,"wins":20},"google/gemini-3.8-flash":{"draws":0,"losses":3,"wins":13},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-4.1":{"draws":1,"losses":1,"wins":6},"gpt-5":{"draws":9,"losses":5,"wins":38},"gpt-5.4":{"draws":5,"losses":4,"wins":7},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":14},"gpt-5.4-nano":{"draws":6,"losses":8,"wins":34},"gpt-5.5":{"draws":18,"losses":5,"wins":17},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":13},"gpt-5.6-sol":{"draws":4,"losses":2,"wins":6},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":3},"gpt-6-astra":{"draws":1,"losses":7,"wins":0},"gpt-6-luna":{"draws":2,"losses":0,"wins":2},"gpt-6-sol":{"draws":0,"losses":6,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":16},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":10},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":9},"meta/muse-spark-1.2":{"draws":2,"losses":1,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":4},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":13},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":1,"wins":25},"o3":{"draws":1,"losses":3,"wins":40},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":5},"poolside/laguna-s-2.1":{"draws":7,"losses":2,"wins":17},"qwen/qwen3.7-max":{"draws":5,"losses":4,"wins":13},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":0,"wins":7},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":12},"qwen/qwen3.8-max":{"draws":4,"losses":4,"wins":8},"qwen/qwen3.8-max-0902":{"draws":3,"losses":0,"wins":5},"stealth/ox-alpha":{"draws":8,"losses":9,"wins":15},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":20},"tencent/hy3-preview":{"draws":12,"losses":0,"wins":14},"tencent/hy4-preview":{"draws":4,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":5,"losses":7,"wins":30},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":5},"x-ai/grok-4.5":{"draws":14,"losses":12,"wins":16},"x-ai/grok-4.6":{"draws":3,"losses":2,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":5},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":0},"z-ai/glm-5.2":{"draws":12,"losses":3,"wins":37},"z-ai/glm-5.3":{"draws":2,"losses":2,"wins":6},"z-ai/glm-5.3-flash":{"draws":0,"losses":5,"wins":7},"z-ai/glm-5.3-flashx":{"draws":3,"losses":0,"wins":5}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":9,"wins":15},"claude-fable-5":{"draws":12,"losses":16,"wins":16},"claude-fable-5-1":{"draws":4,"losses":40,"wins":4},"claude-opus-4-5":{"draws":29,"losses":17,"wins":30},"claude-opus-4-8":{"draws":2,"losses":4,"wins":4},"claude-opus-5":{"draws":3,"losses":24,"wins":3},"claude-opus-5-5":{"draws":1,"losses":3,"wins":0},"claude-sonnet-5":{"draws":29,"losses":24,"wins":45},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-flash":{"draws":29,"losses":4,"wins":19},"deepseek/deepseek-v4-pro":{"draws":14,"losses":10,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":7,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":21,"losses":11,"wins":18},"google/gemini-3.5-flash-lite":{"draws":71,"losses":24,"wins":81},"google/gemini-3.6-flash":{"draws":43,"losses":48,"wins":57},"google/gemini-3.8-flash":{"draws":12,"losses":18,"wins":26},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":7,"wins":3},"gpt-5.4":{"draws":38,"losses":41,"wins":20},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":5,"wins":12},"gpt-5.5":{"draws":4,"losses":9,"wins":3},"gpt-5.6-luna":{"draws":34,"losses":8,"wins":25},"gpt-5.6-sol":{"draws":16,"losses":45,"wins":29},"gpt-5.6-terra":{"draws":20,"losses":7,"wins":25},"gpt-6-astra":{"draws":9,"losses":39,"wins":0},"gpt-6-luna":{"draws":2,"losses":0,"wins":2},"gpt-6-sol":{"draws":1,"losses":4,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":21,"losses":2,"wins":9},"inclusionai/ling-3.0-flash":{"draws":8,"losses":5,"wins":15},"meituan/longcat-2.0":{"draws":15,"losses":7,"wins":24},"meta/muse-glimmer-30b":{"draws":21,"losses":1,"wins":14},"meta/muse-spark-1.2":{"draws":12,"losses":24,"wins":26},"meta/muse-spark-1.3":{"draws":9,"losses":13,"wins":12},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":15,"losses":1,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":32,"losses":21,"wins":33},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":6},"o3":{"draws":14,"losses":17,"wins":59},"openai/gpt-oss-120b":{"draws":23,"losses":4,"wins":13},"poolside/laguna-s-2.1":{"draws":28,"losses":8,"wins":24},"qwen/qwen3.7-max":{"draws":1,"losses":3,"wins":6},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":5,"wins":19},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":6},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":10},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":10},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":38,"losses":52,"wins":51},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":9},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":20,"losses":8,"wins":14},"thinkingmachines/inkling":{"draws":23,"losses":5,"wins":42},"thinkingmachines/inkling-small":{"draws":25,"losses":10,"wins":17},"x-ai/grok-4.5":{"draws":10,"losses":13,"wins":47},"x-ai/grok-4.6":{"draws":11,"losses":22,"wins":17},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":12,"losses":0,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":5},"z-ai/glm-5.2":{"draws":27,"losses":16,"wins":13},"z-ai/glm-5.3":{"draws":12,"losses":28,"wins":10},"z-ai/glm-5.3-flash":{"draws":14,"losses":17,"wins":19},"z-ai/glm-5.3-flashx":{"draws":2,"losses":2,"wins":4}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":3,"wins":19},"claude-fable-5":{"draws":4,"losses":17,"wins":35},"claude-fable-5-1":{"draws":6,"losses":38,"wins":18},"claude-opus-4-5":{"draws":3,"losses":18,"wins":67},"claude-opus-4-8":{"draws":6,"losses":1,"wins":7},"claude-opus-5":{"draws":4,"losses":32,"wins":4},"claude-opus-5-5":{"draws":1,"losses":2,"wins":1},"claude-sonnet-5":{"draws":0,"losses":6,"wins":104},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":4,"losses":5,"wins":33},"deepseek/deepseek-v4-pro":{"draws":1,"losses":5,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":0,"wins":29},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":1,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":11,"wins":37},"google/gemini-3.5-flash-lite":{"draws":8,"losses":3,"wins":145},"google/gemini-3.6-flash":{"draws":9,"losses":28,"wins":99},"google/gemini-3.8-flash":{"draws":6,"losses":10,"wins":38},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-4.1":{"draws":2,"losses":0,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":8},"gpt-5.4":{"draws":7,"losses":25,"wins":62},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":14},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":16},"gpt-5.5":{"draws":2,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":10,"wins":76},"gpt-5.6-sol":{"draws":4,"losses":6,"wins":62},"gpt-5.6-terra":{"draws":5,"losses":6,"wins":39},"gpt-6-astra":{"draws":7,"losses":47,"wins":8},"gpt-6-luna":{"draws":0,"losses":1,"wins":11},"gpt-6-sol":{"draws":1,"losses":5,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":7},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":19},"meituan/longcat-2.0":{"draws":2,"losses":3,"wins":47},"meta/muse-glimmer-30b":{"draws":1,"losses":1,"wins":12},"meta/muse-spark-1.2":{"draws":2,"losses":4,"wins":60},"meta/muse-spark-1.3":{"draws":6,"losses":9,"wins":37},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":5},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":8,"wins":68},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":1,"wins":10},"o3":{"draws":0,"losses":14,"wins":72},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":19},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":51},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":5,"wins":32},"qwen/qwen3.8-27b":{"draws":1,"losses":6,"wins":19},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":22},"qwen/qwen3.8-max":{"draws":3,"losses":3,"wins":40},"qwen/qwen3.8-max-0902":{"draws":0,"losses":0,"wins":6},"stealth/ox-alpha":{"draws":14,"losses":20,"wins":129},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":14},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":5,"losses":14,"wins":23},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":44},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":27},"x-ai/grok-4.5":{"draws":7,"losses":6,"wins":51},"x-ai/grok-4.6":{"draws":7,"losses":16,"wins":33},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":5},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":2},"z-ai/glm-5.2":{"draws":3,"losses":2,"wins":37},"z-ai/glm-5.3":{"draws":6,"losses":17,"wins":33},"z-ai/glm-5.3-flash":{"draws":6,"losses":12,"wins":32},"z-ai/glm-5.3-flashx":{"draws":2,"losses":0,"wins":2}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":6,"wins":20},"claude-fable-5":{"draws":17,"losses":23,"wins":12},"claude-fable-5-1":{"draws":3,"losses":38,"wins":1},"claude-opus-4-5":{"draws":13,"losses":17,"wins":16},"claude-opus-4-8":{"draws":3,"losses":10,"wins":5},"claude-opus-5":{"draws":2,"losses":15,"wins":1},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":16,"losses":12,"wins":22},"cohere/north-mini-code":{"draws":2,"losses":3,"wins":9},"deepseek/deepseek-v4-flash":{"draws":17,"losses":9,"wins":26},"deepseek/deepseek-v4-pro":{"draws":10,"losses":13,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":16,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":16},"google/gemini-3.5-flash":{"draws":15,"losses":11,"wins":28},"google/gemini-3.5-flash-lite":{"draws":23,"losses":13,"wins":46},"google/gemini-3.6-flash":{"draws":22,"losses":29,"wins":23},"google/gemini-3.8-flash":{"draws":9,"losses":18,"wins":15},"gpt-4.1":{"draws":0,"losses":1,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":4,"losses":2,"wins":6},"gpt-5.4":{"draws":14,"losses":19,"wins":7},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":8},"gpt-5.4-nano":{"draws":1,"losses":4,"wins":3},"gpt-5.5":{"draws":4,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":10,"losses":13,"wins":19},"gpt-5.6-sol":{"draws":10,"losses":28,"wins":12},"gpt-5.6-terra":{"draws":9,"losses":14,"wins":11},"gpt-6-astra":{"draws":2,"losses":46,"wins":2},"gpt-6-luna":{"draws":0,"losses":4,"wins":4},"gpt-6-sol":{"draws":2,"losses":9,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":18,"losses":5,"wins":13},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":6,"losses":8,"wins":14},"meta/muse-glimmer-30b":{"draws":18,"losses":7,"wins":17},"meta/muse-spark-1.2":{"draws":9,"losses":17,"wins":6},"meta/muse-spark-1.3":{"draws":10,"losses":19,"wins":15},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":17,"losses":7,"wins":16},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":12},"o3":{"draws":2,"losses":16,"wins":30},"openai/gpt-oss-120b":{"draws":10,"losses":6,"wins":28},"poolside/laguna-s-2.1":{"draws":10,"losses":3,"wins":19},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":12},"qwen/qwen3.7-plus":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":11},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":17},"qwen/qwen3.8-flash":{"draws":6,"losses":11,"wins":17},"qwen/qwen3.8-max":{"draws":19,"losses":19,"wins":12},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":1},"stealth/ox-alpha":{"draws":43,"losses":51,"wins":52},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":14,"wins":19},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":29},"thinkingmachines/inkling-small":{"draws":18,"losses":6,"wins":28},"x-ai/grok-4.5":{"draws":14,"losses":25,"wins":13},"x-ai/grok-4.6":{"draws":16,"losses":28,"wins":6},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":3},"z-ai/glm-5.2":{"draws":28,"losses":14,"wins":30},"z-ai/glm-5.3":{"draws":20,"losses":24,"wins":8},"z-ai/glm-5.3-flash":{"draws":8,"losses":19,"wins":15},"z-ai/glm-5.3-flashx":{"draws":2,"losses":2,"wins":2}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":20},"claude-fable-5":{"draws":3,"losses":10,"wins":43},"claude-fable-5-1":{"draws":5,"losses":16,"wins":47},"claude-opus-4-5":{"draws":1,"losses":1,"wins":46},"claude-opus-4-8":{"draws":1,"losses":0,"wins":17},"claude-opus-5":{"draws":3,"losses":2,"wins":23},"claude-opus-5-5":{"draws":0,"losses":3,"wins":9},"claude-sonnet-5":{"draws":0,"losses":2,"wins":54},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":35},"deepseek/deepseek-v4-pro":{"draws":3,"losses":2,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":11},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":50},"google/gemini-3.5-flash-lite":{"draws":3,"losses":0,"wins":53},"google/gemini-3.6-flash":{"draws":3,"losses":1,"wins":56},"google/gemini-3.8-flash":{"draws":5,"losses":1,"wins":44},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":0,"wins":10},"gpt-5.4":{"draws":2,"losses":7,"wins":43},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":14},"gpt-5.5":{"draws":0,"losses":0,"wins":8},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":29},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":52},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":45},"gpt-6-astra":{"draws":0,"losses":8,"wins":26},"gpt-6-luna":{"draws":2,"losses":0,"wins":4},"gpt-6-sol":{"draws":0,"losses":0,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":24},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":22},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":30},"meta/muse-spark-1.3":{"draws":2,"losses":1,"wins":43},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":40},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":10},"o3":{"draws":0,"losses":1,"wins":39},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":24},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":22},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":1,"wins":43},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":22},"qwen/qwen3.8-flash":{"draws":1,"losses":0,"wins":25},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":39},"qwen/qwen3.8-max-0902":{"draws":1,"losses":0,"wins":11},"stealth/ox-alpha":{"draws":7,"losses":4,"wins":151},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":0,"losses":5,"wins":37},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":22},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":30},"x-ai/grok-4.5":{"draws":1,"losses":0,"wins":33},"x-ai/grok-4.6":{"draws":0,"losses":2,"wins":54},"x-ai/grok-4.7":{"draws":0,"losses":0,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":1,"losses":0,"wins":41},"z-ai/glm-5.3":{"draws":3,"losses":0,"wins":47},"z-ai/glm-5.3-flash":{"draws":7,"losses":2,"wins":43},"z-ai/glm-5.3-flashx":{"draws":0,"losses":0,"wins":10}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":1},"claude-fable-5":{"draws":4,"losses":6,"wins":2},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":3,"losses":2,"wins":5},"claude-opus-4-8":{"draws":0,"losses":3,"wins":3},"claude-opus-5":{"draws":0,"losses":11,"wins":1},"claude-opus-5-5":{"draws":8,"losses":43,"wins":1},"claude-sonnet-5":{"draws":1,"losses":0,"wins":3},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":0,"losses":3,"wins":5},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":5,"wins":7},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":1,"losses":3,"wins":18},"google/gemini-3.6-flash":{"draws":2,"losses":10,"wins":8},"google/gemini-3.8-flash":{"draws":2,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":3},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":8,"wins":4},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":4},"gpt-5.5":{"draws":1,"losses":0,"wins":3},"gpt-5.6-luna":{"draws":1,"losses":2,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":5},"gpt-5.6-terra":{"draws":0,"losses":3,"wins":1},"gpt-6-astra":{"draws":5,"losses":2,"wins":1},"gpt-6-luna":{"draws":4,"losses":9,"wins":17},"gpt-6-sol":{"draws":7,"losses":32,"wins":9},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":1,"wins":9},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":7},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":8},"meta/muse-glimmer-30b":{"draws":0,"losses":3,"wins":7},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":2},"meta/muse-spark-1.3":{"draws":1,"losses":2,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":7},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":6},"o3":{"draws":0,"losses":2,"wins":6},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":8},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":9},"stealth/ox-alpha":{"draws":2,"losses":6,"wins":10},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":3},"tencent/hy4-preview":{"draws":1,"losses":4,"wins":5},"thinkingmachines/inkling":{"draws":4,"losses":1,"wins":7},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":4,"losses":3,"wins":5},"x-ai/grok-4.6":{"draws":0,"losses":2,"wins":2},"x-ai/grok-4.7":{"draws":3,"losses":18,"wins":7},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":3,"losses":4,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":4,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":12,"wins":8},"z-ai/glm-5.2":{"draws":2,"losses":2,"wins":6},"z-ai/glm-5.3":{"draws":2,"losses":3,"wins":3},"z-ai/glm-5.3-flash":{"draws":1,"losses":3,"wins":4},"z-ai/glm-5.3-flashx":{"draws":6,"losses":12,"wins":14}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":6},"claude-fable-5":{"draws":0,"losses":0,"wins":2},"claude-fable-5-1":{"draws":0,"losses":0,"wins":6},"claude-opus-4-5":{"draws":0,"losses":5,"wins":13},"claude-opus-4-8":{"draws":0,"losses":1,"wins":3},"claude-opus-5":{"draws":1,"losses":3,"wins":4},"claude-opus-5-5":{"draws":6,"losses":27,"wins":19},"claude-sonnet-5":{"draws":0,"losses":0,"wins":10},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":15},"deepseek/deepseek-v4-pro":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":0,"wins":6},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":10},"google/gemini-3.5-flash-lite":{"draws":1,"losses":4,"wins":17},"google/gemini-3.6-flash":{"draws":1,"losses":1,"wins":8},"google/gemini-3.8-flash":{"draws":0,"losses":2,"wins":8},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":8},"gpt-5.4":{"draws":1,"losses":0,"wins":7},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":8},"gpt-5.5":{"draws":0,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":6},"gpt-5.6-terra":{"draws":0,"losses":1,"wins":3},"gpt-6-astra":{"draws":0,"losses":8,"wins":2},"gpt-6-luna":{"draws":4,"losses":5,"wins":37},"gpt-6-sol":{"draws":3,"losses":8,"wins":21},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":1,"losses":2,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":10},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":6},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":8},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":1,"losses":2,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":6},"o3":{"draws":0,"losses":0,"wins":8},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":4,"wins":6},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":0,"losses":4,"wins":4},"qwen/qwen3.8-max-0902":{"draws":1,"losses":3,"wins":14},"stealth/ox-alpha":{"draws":5,"losses":4,"wins":21},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":2,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":12},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":14},"x-ai/grok-4.5":{"draws":0,"losses":3,"wins":5},"x-ai/grok-4.6":{"draws":0,"losses":0,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":10,"wins":16},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":1,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":7,"wins":13},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":12},"z-ai/glm-5.3":{"draws":4,"losses":1,"wins":5},"z-ai/glm-5.3-flash":{"draws":3,"losses":2,"wins":3},"z-ai/glm-5.3-flashx":{"draws":6,"losses":4,"wins":26}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":3,"wins":0},"claude-fable-5":{"draws":4,"losses":0,"wins":0},"claude-opus-4-5":{"draws":0,"losses":2,"wins":0},"claude-opus-4-8":{"draws":4,"losses":0,"wins":0},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":7,"losses":1,"wins":0},"deepseek/deepseek-v4-pro":{"draws":5,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":4,"wins":0},"google/gemini-3.5-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.5-flash-lite":{"draws":11,"losses":1,"wins":0},"google/gemini-3.6-flash":{"draws":4,"losses":2,"wins":0},"google/gemini-3.8-flash":{"draws":1,"losses":3,"wins":0},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":9,"losses":1,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":4,"losses":0,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":0},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":2,"wins":0},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":0},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":1,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":0},"o3":{"draws":2,"losses":0,"wins":0},"openai/gpt-oss-120b":{"draws":4,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-flash":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":23,"losses":8,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":0},"tencent/hy4-preview":{"draws":1,"losses":1,"wins":0},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":0},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.6":{"draws":6,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":0},"z-ai/glm-5.3":{"draws":2,"losses":0,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":8,"wins":12},"claude-fable-5":{"draws":7,"losses":13,"wins":0},"claude-fable-5-1":{"draws":0,"losses":14,"wins":0},"claude-opus-4-5":{"draws":19,"losses":17,"wins":0},"claude-opus-4-8":{"draws":0,"losses":8,"wins":0},"claude-opus-5":{"draws":3,"losses":8,"wins":1},"claude-opus-5-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":16,"losses":22,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":6,"wins":6},"deepseek/deepseek-v4-flash":{"draws":18,"losses":19,"wins":3},"deepseek/deepseek-v4-pro":{"draws":16,"losses":11,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":15,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":18,"losses":14,"wins":0},"google/gemini-3.5-flash-lite":{"draws":37,"losses":30,"wins":5},"google/gemini-3.6-flash":{"draws":30,"losses":36,"wins":4},"google/gemini-3.8-flash":{"draws":12,"losses":19,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":0},"gpt-4.1":{"draws":1,"losses":5,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":15,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":0,"losses":4,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":4},"gpt-5.5":{"draws":7,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":20,"losses":9,"wins":7},"gpt-5.6-sol":{"draws":7,"losses":17,"wins":0},"gpt-5.6-terra":{"draws":14,"losses":18,"wins":4},"gpt-6-astra":{"draws":4,"losses":18,"wins":0},"gpt-6-luna":{"draws":5,"losses":4,"wins":1},"gpt-6-sol":{"draws":1,"losses":3,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":11,"losses":6,"wins":5},"meituan/longcat-2.0":{"draws":10,"losses":15,"wins":5},"meta/muse-glimmer-30b":{"draws":22,"losses":16,"wins":6},"meta/muse-spark-1.2":{"draws":12,"losses":26,"wins":0},"meta/muse-spark-1.3":{"draws":9,"losses":10,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":0},"mistralai/mistral-medium-3-5":{"draws":15,"losses":10,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":15,"losses":14,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":6},"o3":{"draws":11,"losses":27,"wins":2},"openai/gpt-oss-120b":{"draws":18,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":14,"losses":12,"wins":2},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":9,"wins":4},"qwen/qwen3.8-27b":{"draws":8,"losses":11,"wins":3},"qwen/qwen3.8-flash":{"draws":13,"losses":15,"wins":2},"qwen/qwen3.8-max":{"draws":19,"losses":13,"wins":4},"qwen/qwen3.8-max-0902":{"draws":6,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":30,"losses":45,"wins":9},"stepfun/step-3.7-flash":{"draws":6,"losses":8,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":11,"losses":19,"wins":2},"thinkingmachines/inkling":{"draws":16,"losses":12,"wins":0},"thinkingmachines/inkling-small":{"draws":23,"losses":17,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":16,"wins":0},"x-ai/grok-4.6":{"draws":10,"losses":5,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":24,"losses":32,"wins":6},"z-ai/glm-5.3":{"draws":14,"losses":9,"wins":1},"z-ai/glm-5.3-flash":{"draws":13,"losses":18,"wins":1},"z-ai/glm-5.3-flashx":{"draws":1,"losses":1,"wins":0}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":8,"wins":14},"claude-fable-5":{"draws":11,"losses":17,"wins":2},"claude-fable-5-1":{"draws":3,"losses":23,"wins":0},"claude-opus-4-5":{"draws":16,"losses":17,"wins":3},"claude-opus-4-8":{"draws":3,"losses":6,"wins":3},"claude-opus-5":{"draws":4,"losses":11,"wins":3},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":20,"losses":16,"wins":10},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":22,"losses":8,"wins":14},"deepseek/deepseek-v4-pro":{"draws":15,"losses":11,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":17,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":1,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":12,"losses":16,"wins":10},"google/gemini-3.5-flash-lite":{"draws":27,"losses":23,"wins":22},"google/gemini-3.6-flash":{"draws":32,"losses":27,"wins":19},"google/gemini-3.8-flash":{"draws":13,"losses":19,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":3},"gpt-4.1":{"draws":2,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":5,"wins":1},"gpt-5.4":{"draws":16,"losses":16,"wins":8},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":0},"gpt-5.5":{"draws":10,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":25,"losses":9,"wins":16},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":4},"gpt-5.6-terra":{"draws":27,"losses":14,"wins":7},"gpt-6-astra":{"draws":4,"losses":30,"wins":0},"gpt-6-luna":{"draws":6,"losses":1,"wins":3},"gpt-6-sol":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":20,"losses":3,"wins":13},"inclusionai/ling-3.0-flash":{"draws":13,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":15,"losses":5,"wins":14},"meta/muse-glimmer-30b":{"draws":13,"losses":2,"wins":11},"meta/muse-spark-1.2":{"draws":9,"losses":11,"wins":10},"meta/muse-spark-1.3":{"draws":16,"losses":4,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":22,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":17,"losses":7,"wins":6},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":4},"o3":{"draws":12,"losses":15,"wins":9},"openai/gpt-oss-120b":{"draws":19,"losses":8,"wins":13},"poolside/laguna-s-2.1":{"draws":17,"losses":4,"wins":11},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":5,"losses":2,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":8,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":8,"wins":6},"qwen/qwen3.8-flash":{"draws":11,"losses":8,"wins":11},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":14},"qwen/qwen3.8-max-0902":{"draws":10,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":37,"losses":64,"wins":25},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":7},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":0},"tencent/hy4-preview":{"draws":14,"losses":16,"wins":8},"thinkingmachines/inkling":{"draws":18,"losses":5,"wins":13},"thinkingmachines/inkling-small":{"draws":24,"losses":4,"wins":20},"x-ai/grok-4.5":{"draws":14,"losses":16,"wins":6},"x-ai/grok-4.6":{"draws":12,"losses":18,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":4,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":22,"losses":23,"wins":11},"z-ai/glm-5.3":{"draws":10,"losses":13,"wins":5},"z-ai/glm-5.3-flash":{"draws":12,"losses":20,"wins":6},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"wins":7},"claude-fable-5":{"draws":5,"losses":2,"wins":7},"claude-fable-5-1":{"draws":1,"losses":11,"wins":2},"claude-opus-4-5":{"draws":5,"losses":5,"wins":12},"claude-opus-4-8":{"draws":0,"losses":2,"wins":2},"claude-opus-5":{"draws":0,"losses":3,"wins":1},"claude-sonnet-5":{"draws":2,"losses":15,"wins":13},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":12},"deepseek/deepseek-v4-pro":{"draws":0,"losses":5,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":3,"wins":8},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":9,"wins":5},"google/gemini-3.5-flash-lite":{"draws":4,"losses":12,"wins":24},"google/gemini-3.6-flash":{"draws":8,"losses":12,"wins":24},"google/gemini-3.8-flash":{"draws":1,"losses":8,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":1,"losses":2,"wins":1},"gpt-5.4":{"draws":1,"losses":20,"wins":7},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.5":{"draws":3,"losses":1,"wins":6},"gpt-5.6-luna":{"draws":0,"losses":9,"wins":19},"gpt-5.6-sol":{"draws":0,"losses":24,"wins":2},"gpt-5.6-terra":{"draws":4,"losses":6,"wins":6},"gpt-6-astra":{"draws":4,"losses":8,"wins":0},"gpt-6-luna":{"draws":0,"losses":2,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":1,"wins":5},"inclusionai/ling-3.0-flash":{"draws":0,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":1},"meta/muse-glimmer-30b":{"draws":0,"losses":3,"wins":7},"meta/muse-spark-1.2":{"draws":2,"losses":5,"wins":9},"meta/muse-spark-1.3":{"draws":2,"losses":7,"wins":7},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":10,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":1},"o3":{"draws":2,"losses":10,"wins":12},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":6},"poolside/laguna-s-2.1":{"draws":1,"losses":5,"wins":8},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.8-27b":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":1,"losses":3,"wins":4},"qwen/qwen3.8-max":{"draws":2,"losses":4,"wins":6},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":0},"stealth/ox-alpha":{"draws":10,"losses":28,"wins":18},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":1},"tencent/hy4-preview":{"draws":3,"losses":6,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":4,"wins":12},"thinkingmachines/inkling-small":{"draws":0,"losses":5,"wins":15},"x-ai/grok-4.5":{"draws":2,"losses":10,"wins":8},"x-ai/grok-4.6":{"draws":4,"losses":8,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":17},"z-ai/glm-5.3":{"draws":5,"losses":5,"wins":6},"z-ai/glm-5.3-flash":{"draws":1,"losses":4,"wins":7},"z-ai/glm-5.3-flashx":{"draws":0,"losses":1,"wins":1}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":19},"claude-fable-5":{"draws":5,"losses":18,"wins":21},"claude-fable-5-1":{"draws":2,"losses":40,"wins":2},"claude-opus-4-5":{"draws":4,"losses":5,"wins":27},"claude-opus-4-8":{"draws":6,"losses":3,"wins":3},"claude-opus-5":{"draws":4,"losses":14,"wins":6},"claude-opus-5-5":{"draws":0,"losses":7,"wins":1},"claude-sonnet-5":{"draws":11,"losses":3,"wins":16},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":4,"losses":4,"wins":26},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":4,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":21},"google/gemini-3.5-flash-lite":{"draws":3,"losses":6,"wins":33},"google/gemini-3.6-flash":{"draws":3,"losses":12,"wins":35},"google/gemini-3.8-flash":{"draws":2,"losses":10,"wins":24},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":5},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":6,"losses":8,"wins":18},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":9},"gpt-5.4-nano":{"draws":5,"losses":2,"wins":9},"gpt-5.5":{"draws":3,"losses":5,"wins":2},"gpt-5.6-luna":{"draws":3,"losses":3,"wins":18},"gpt-5.6-sol":{"draws":11,"losses":12,"wins":25},"gpt-5.6-terra":{"draws":8,"losses":4,"wins":28},"gpt-6-astra":{"draws":5,"losses":36,"wins":5},"gpt-6-luna":{"draws":1,"losses":1,"wins":2},"gpt-6-sol":{"draws":2,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":4,"losses":2,"wins":2},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":8,"losses":3,"wins":13},"meta/muse-spark-1.3":{"draws":2,"losses":5,"wins":11},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":10,"losses":5,"wins":17},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":9},"o3":{"draws":0,"losses":3,"wins":33},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":12},"poolside/laguna-s-2.1":{"draws":10,"losses":0,"wins":12},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":12,"wins":21},"qwen/qwen3.8-27b":{"draws":1,"losses":5,"wins":12},"qwen/qwen3.8-flash":{"draws":7,"losses":2,"wins":13},"qwen/qwen3.8-max":{"draws":6,"losses":5,"wins":23},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":5},"stealth/ox-alpha":{"draws":25,"losses":36,"wins":56},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":5,"losses":15,"wins":14},"thinkingmachines/inkling":{"draws":5,"losses":1,"wins":6},"thinkingmachines/inkling-small":{"draws":6,"losses":2,"wins":14},"x-ai/grok-4.5":{"draws":3,"losses":6,"wins":15},"x-ai/grok-4.6":{"draws":12,"losses":14,"wins":20},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":4},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":14},"z-ai/glm-5.3":{"draws":13,"losses":18,"wins":11},"z-ai/glm-5.3-flash":{"draws":8,"losses":14,"wins":14},"z-ai/glm-5.3-flashx":{"draws":4,"losses":1,"wins":1}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":11,"wins":11},"claude-fable-5":{"draws":15,"losses":11,"wins":6},"claude-fable-5-1":{"draws":1,"losses":21,"wins":0},"claude-opus-4-5":{"draws":12,"losses":25,"wins":7},"claude-opus-4-8":{"draws":4,"losses":12,"wins":0},"claude-opus-5":{"draws":7,"losses":9,"wins":2},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":23,"losses":14,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":6,"wins":3},"deepseek/deepseek-v4-flash":{"draws":21,"losses":15,"wins":12},"deepseek/deepseek-v4-pro":{"draws":10,"losses":18,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":4},"google/gemini-3.5-flash":{"draws":13,"losses":20,"wins":9},"google/gemini-3.5-flash-lite":{"draws":35,"losses":28,"wins":17},"google/gemini-3.6-flash":{"draws":20,"losses":23,"wins":13},"google/gemini-3.8-flash":{"draws":11,"losses":16,"wins":5},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":3},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":2,"losses":3,"wins":3},"gpt-5.4":{"draws":18,"losses":10,"wins":4},"gpt-5.4-mini":{"draws":1,"losses":5,"wins":0},"gpt-5.4-nano":{"draws":4,"losses":5,"wins":3},"gpt-5.5":{"draws":7,"losses":3,"wins":0},"gpt-5.6-luna":{"draws":25,"losses":17,"wins":4},"gpt-5.6-sol":{"draws":9,"losses":29,"wins":2},"gpt-5.6-terra":{"draws":16,"losses":23,"wins":7},"gpt-6-astra":{"draws":1,"losses":29,"wins":0},"gpt-6-luna":{"draws":3,"losses":1,"wins":0},"gpt-6-sol":{"draws":3,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":19,"losses":8,"wins":15},"inclusionai/ling-3.0-flash":{"draws":9,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":16,"losses":10,"wins":12},"meta/muse-glimmer-30b":{"draws":26,"losses":16,"wins":6},"meta/muse-spark-1.2":{"draws":11,"losses":14,"wins":5},"meta/muse-spark-1.3":{"draws":13,"losses":15,"wins":4},"minimax/minimax-m3":{"draws":1,"losses":7,"wins":4},"mistralai/mistral-medium-3-5":{"draws":8,"losses":1,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":18,"wins":7},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":4,"wins":1},"o3":{"draws":6,"losses":30,"wins":8},"openai/gpt-oss-120b":{"draws":21,"losses":6,"wins":11},"poolside/laguna-s-2.1":{"draws":14,"losses":11,"wins":11},"qwen/qwen3.7-max":{"draws":6,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":23,"wins":2},"qwen/qwen3.8-27b":{"draws":4,"losses":11,"wins":5},"qwen/qwen3.8-flash":{"draws":11,"losses":11,"wins":4},"qwen/qwen3.8-max":{"draws":16,"losses":20,"wins":6},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":36,"losses":63,"wins":31},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":4},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":18,"losses":16,"wins":4},"thinkingmachines/inkling":{"draws":15,"losses":13,"wins":10},"thinkingmachines/inkling-small":{"draws":23,"losses":19,"wins":6},"x-ai/grok-4.5":{"draws":10,"losses":20,"wins":4},"x-ai/grok-4.6":{"draws":15,"losses":15,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":3,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":0},"z-ai/glm-5.2":{"draws":28,"losses":26,"wins":16},"z-ai/glm-5.3":{"draws":16,"losses":10,"wins":6},"z-ai/glm-5.3-flash":{"draws":9,"losses":14,"wins":9},"z-ai/glm-5.3-flashx":{"draws":5,"losses":2,"wins":1}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":0,"wins":4},"claude-fable-5":{"draws":5,"losses":19,"wins":8},"claude-fable-5-1":{"draws":5,"losses":42,"wins":1},"claude-opus-4-5":{"draws":32,"losses":7,"wins":27},"claude-opus-4-8":{"draws":10,"losses":6,"wins":6},"claude-opus-5":{"draws":6,"losses":31,"wins":3},"claude-opus-5-5":{"draws":1,"losses":9,"wins":0},"claude-sonnet-5":{"draws":18,"losses":11,"wins":25},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":11,"losses":10,"wins":15},"deepseek/deepseek-v4-pro":{"draws":9,"losses":4,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":5,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":3},"google/gemini-3.5-flash":{"draws":14,"losses":13,"wins":7},"google/gemini-3.5-flash-lite":{"draws":36,"losses":16,"wins":60},"google/gemini-3.6-flash":{"draws":23,"losses":44,"wins":47},"google/gemini-3.8-flash":{"draws":8,"losses":9,"wins":13},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":5,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":2,"wins":8},"gpt-5.4":{"draws":20,"losses":15,"wins":17},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":2},"gpt-5.4-nano":{"draws":7,"losses":0,"wins":1},"gpt-5.5":{"draws":5,"losses":4,"wins":5},"gpt-5.6-luna":{"draws":18,"losses":13,"wins":21},"gpt-5.6-sol":{"draws":26,"losses":30,"wins":10},"gpt-5.6-terra":{"draws":13,"losses":5,"wins":16},"gpt-6-astra":{"draws":8,"losses":27,"wins":1},"gpt-6-luna":{"draws":4,"losses":3,"wins":5},"gpt-6-sol":{"draws":1,"losses":2,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":8},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":23},"meituan/longcat-2.0":{"draws":13,"losses":3,"wins":24},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":14},"meta/muse-spark-1.2":{"draws":4,"losses":20,"wins":18},"meta/muse-spark-1.3":{"draws":13,"losses":5,"wins":16},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":20,"losses":4,"wins":30},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":7},"o3":{"draws":0,"losses":20,"wins":36},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":19},"poolside/laguna-s-2.1":{"draws":20,"losses":8,"wins":16},"qwen/qwen3.7-max":{"draws":5,"losses":0,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":5,"wins":13},"qwen/qwen3.8-27b":{"draws":6,"losses":4,"wins":4},"qwen/qwen3.8-flash":{"draws":9,"losses":2,"wins":5},"qwen/qwen3.8-max":{"draws":9,"losses":9,"wins":10},"qwen/qwen3.8-max-0902":{"draws":3,"losses":1,"wins":2},"stealth/ox-alpha":{"draws":27,"losses":44,"wins":37},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":10,"losses":5,"wins":17},"thinkingmachines/inkling":{"draws":22,"losses":6,"wins":22},"thinkingmachines/inkling-small":{"draws":9,"losses":1,"wins":16},"x-ai/grok-4.5":{"draws":26,"losses":28,"wins":18},"x-ai/grok-4.6":{"draws":14,"losses":12,"wins":8},"x-ai/grok-4.7":{"draws":3,"losses":1,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":3,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":2},"z-ai/glm-5.2":{"draws":13,"losses":3,"wins":10},"z-ai/glm-5.3":{"draws":9,"losses":14,"wins":5},"z-ai/glm-5.3-flash":{"draws":12,"losses":17,"wins":5},"z-ai/glm-5.3-flashx":{"draws":1,"losses":2,"wins":5}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":4,"wins":8},"claude-fable-5":{"draws":4,"losses":6,"wins":0},"claude-fable-5-1":{"draws":2,"losses":14,"wins":0},"claude-opus-4-5":{"draws":40,"losses":41,"wins":7},"claude-opus-4-8":{"draws":15,"losses":35,"wins":6},"claude-opus-5":{"draws":12,"losses":50,"wins":0},"claude-opus-5-5":{"draws":0,"losses":16,"wins":0},"claude-sonnet-5":{"draws":12,"losses":7,"wins":3},"cohere/north-mini-code":{"draws":10,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":30,"losses":7,"wins":15},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":9,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":23,"losses":9,"wins":19},"google/gemini-3.5-flash":{"draws":11,"losses":5,"wins":4},"google/gemini-3.5-flash-lite":{"draws":22,"losses":19,"wins":15},"google/gemini-3.6-flash":{"draws":17,"losses":25,"wins":4},"google/gemini-3.8-flash":{"draws":3,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":12,"losses":2,"wins":2},"gpt-4.1":{"draws":10,"losses":4,"wins":4},"gpt-5":{"draws":22,"losses":21,"wins":3},"gpt-5.4":{"draws":4,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":22,"losses":12,"wins":6},"gpt-5.4-nano":{"draws":18,"losses":14,"wins":12},"gpt-5.5":{"draws":22,"losses":24,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":1,"losses":9,"wins":0},"gpt-5.6-terra":{"draws":11,"losses":7,"wins":2},"gpt-6-astra":{"draws":0,"losses":10,"wins":0},"gpt-6-luna":{"draws":6,"losses":7,"wins":1},"gpt-6-sol":{"draws":1,"losses":9,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":3,"wins":2},"inclusionai/ling-3.0-flash":{"draws":9,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":19,"losses":6,"wins":13},"meta/muse-glimmer-30b":{"draws":10,"losses":3,"wins":1},"meta/muse-spark-1.2":{"draws":4,"losses":10,"wins":0},"meta/muse-spark-1.3":{"draws":5,"losses":7,"wins":2},"minimax/minimax-m3":{"draws":18,"losses":6,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":3,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":11,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":20,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":10,"wins":5},"o3":{"draws":18,"losses":33,"wins":13},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":13,"losses":7,"wins":6},"qwen/qwen3.7-max":{"draws":27,"losses":2,"wins":1},"qwen/qwen3.7-plus":{"draws":23,"losses":3,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.8-27b":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.8-flash":{"draws":9,"losses":3,"wins":2},"qwen/qwen3.8-max":{"draws":5,"losses":7,"wins":2},"qwen/qwen3.8-max-0902":{"draws":6,"losses":6,"wins":2},"stealth/ox-alpha":{"draws":13,"losses":31,"wins":4},"stepfun/step-3.7-flash":{"draws":18,"losses":6,"wins":10},"tencent/hy3-preview":{"draws":31,"losses":11,"wins":4},"tencent/hy4-preview":{"draws":6,"losses":7,"wins":1},"thinkingmachines/inkling":{"draws":29,"losses":17,"wins":32},"thinkingmachines/inkling-small":{"draws":9,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":13,"losses":19,"wins":0},"x-ai/grok-4.6":{"draws":7,"losses":3,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":16,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":59,"losses":11,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":8,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":2,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":46,"losses":29,"wins":9},"z-ai/glm-5.3":{"draws":1,"losses":12,"wins":1},"z-ai/glm-5.3-flash":{"draws":5,"losses":6,"wins":3},"z-ai/glm-5.3-flashx":{"draws":6,"losses":8,"wins":0}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":35,"wins":61},"claude-fable-5":{"draws":7,"losses":86,"wins":19},"claude-fable-5-1":{"draws":0,"losses":105,"wins":5},"claude-opus-4-5":{"draws":29,"losses":163,"wins":80},"claude-opus-4-8":{"draws":0,"losses":51,"wins":13},"claude-opus-5":{"draws":2,"losses":109,"wins":5},"claude-opus-5-5":{"draws":0,"losses":28,"wins":0},"claude-sonnet-5":{"draws":15,"losses":101,"wins":124},"cohere/north-mini-code":{"draws":4,"losses":10,"wins":12},"deepseek/deepseek-v4-flash":{"draws":13,"losses":48,"wins":71},"deepseek/deepseek-v4-pro":{"draws":14,"losses":56,"wins":42},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":54,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":13,"wins":6},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":39},"google/gemini-3.5-flash":{"draws":14,"losses":71,"wins":35},"google/gemini-3.5-flash-lite":{"draws":70,"losses":153,"wins":329},"google/gemini-3.6-flash":{"draws":62,"losses":263,"wins":183},"google/gemini-3.8-flash":{"draws":13,"losses":73,"wins":36},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":14},"gpt-4.1":{"draws":0,"losses":10,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":6},"gpt-5":{"draws":10,"losses":38,"wins":24},"gpt-5.4":{"draws":19,"losses":144,"wins":47},"gpt-5.4-mini":{"draws":4,"losses":1,"wins":11},"gpt-5.4-nano":{"draws":2,"losses":22,"wins":28},"gpt-5.5":{"draws":4,"losses":38,"wins":8},"gpt-5.6-luna":{"draws":28,"losses":89,"wins":113},"gpt-5.6-sol":{"draws":9,"losses":163,"wins":46},"gpt-5.6-terra":{"draws":12,"losses":57,"wins":55},"gpt-6-astra":{"draws":1,"losses":100,"wins":1},"gpt-6-luna":{"draws":3,"losses":6,"wins":5},"gpt-6-sol":{"draws":0,"losses":13,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":12},"inception/mercury-2.5-preview":{"draws":12,"losses":10,"wins":54},"inclusionai/ling-3.0-flash":{"draws":6,"losses":21,"wins":65},"meituan/longcat-2.0":{"draws":13,"losses":49,"wins":110},"meta/muse-glimmer-30b":{"draws":18,"losses":13,"wins":61},"meta/muse-spark-1.2":{"draws":12,"losses":52,"wins":90},"meta/muse-spark-1.3":{"draws":4,"losses":73,"wins":33},"minimax/minimax-m3":{"draws":2,"losses":8,"wins":20},"mistralai/mistral-medium-3-5":{"draws":10,"losses":8,"wins":46},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":28,"losses":98,"wins":122},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":14,"wins":46},"o3":{"draws":28,"losses":152,"wins":180},"openai/gpt-oss-120b":{"draws":15,"losses":19,"wins":66},"poolside/laguna-s-2.1":{"draws":34,"losses":41,"wins":69},"qwen/qwen3.7-max":{"draws":4,"losses":5,"wins":17},"qwen/qwen3.7-plus":{"draws":2,"losses":7,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":63,"wins":41},"qwen/qwen3.8-27b":{"draws":16,"losses":46,"wins":28},"qwen/qwen3.8-flash":{"draws":19,"losses":30,"wins":35},"qwen/qwen3.8-max":{"draws":18,"losses":69,"wins":41},"qwen/qwen3.8-max-0902":{"draws":0,"losses":13,"wins":3},"stealth/ox-alpha":{"draws":34,"losses":152,"wins":156},"stepfun/step-3.7-flash":{"draws":19,"losses":39,"wins":88},"tencent/hy3-preview":{"draws":7,"losses":15,"wins":20},"tencent/hy4-preview":{"draws":14,"losses":57,"wins":49},"thinkingmachines/inkling":{"draws":29,"losses":46,"wins":140},"thinkingmachines/inkling-small":{"draws":30,"losses":39,"wins":58},"x-ai/grok-4.5":{"draws":9,"losses":135,"wins":70},"x-ai/grok-4.6":{"draws":16,"losses":55,"wins":39},"x-ai/grok-4.7":{"draws":0,"losses":11,"wins":3},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":5},"xiaomi/mimo-v2.5":{"draws":5,"losses":9,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":17,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":13,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":18,"losses":49,"wins":79},"z-ai/glm-5.3":{"draws":8,"losses":76,"wins":26},"z-ai/glm-5.3-flash":{"draws":15,"losses":57,"wins":48},"z-ai/glm-5.3-flashx":{"draws":1,"losses":15,"wins":8}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":11,"wins":10},"claude-fable-5":{"draws":13,"losses":14,"wins":7},"claude-fable-5-1":{"draws":2,"losses":26,"wins":0},"claude-opus-4-5":{"draws":4,"losses":15,"wins":9},"claude-opus-5":{"draws":2,"losses":18,"wins":0},"claude-opus-5-5":{"draws":0,"losses":24,"wins":0},"claude-sonnet-5":{"draws":12,"losses":23,"wins":5},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":19,"losses":13,"wins":16},"deepseek/deepseek-v4-pro":{"draws":19,"losses":8,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":9,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":5,"wins":5},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":5},"google/gemini-3.5-flash":{"draws":17,"losses":15,"wins":10},"google/gemini-3.5-flash-lite":{"draws":34,"losses":21,"wins":23},"google/gemini-3.6-flash":{"draws":25,"losses":31,"wins":10},"google/gemini-3.8-flash":{"draws":5,"losses":17,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":1,"wins":1},"gpt-5.4":{"draws":22,"losses":7,"wins":7},"gpt-5.4-mini":{"draws":2,"losses":4,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":4},"gpt-5.5":{"draws":4,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":22,"losses":4,"wins":10},"gpt-5.6-sol":{"draws":7,"losses":21,"wins":6},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":8},"gpt-6-astra":{"draws":2,"losses":18,"wins":0},"gpt-6-luna":{"draws":2,"losses":2,"wins":0},"gpt-6-sol":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":19,"losses":7,"wins":8},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":16},"meituan/longcat-2.0":{"draws":11,"losses":15,"wins":16},"meta/muse-glimmer-30b":{"draws":15,"losses":10,"wins":9},"meta/muse-spark-1.2":{"draws":9,"losses":14,"wins":5},"meta/muse-spark-1.3":{"draws":7,"losses":17,"wins":4},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":7},"mistralai/mistral-medium-3-5":{"draws":15,"losses":3,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":13,"wins":10},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":6,"wins":8},"o3":{"draws":13,"losses":22,"wins":11},"openai/gpt-oss-120b":{"draws":15,"losses":3,"wins":10},"poolside/laguna-s-2.1":{"draws":16,"losses":5,"wins":7},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":16,"wins":6},"qwen/qwen3.8-27b":{"draws":4,"losses":14,"wins":8},"qwen/qwen3.8-flash":{"draws":12,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":15,"losses":25,"wins":4},"qwen/qwen3.8-max-0902":{"draws":2,"losses":12,"wins":2},"stealth/ox-alpha":{"draws":31,"losses":46,"wins":30},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":5},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":10,"losses":12,"wins":6},"thinkingmachines/inkling":{"draws":12,"losses":9,"wins":5},"thinkingmachines/inkling-small":{"draws":24,"losses":12,"wins":8},"x-ai/grok-4.5":{"draws":13,"losses":12,"wins":3},"x-ai/grok-4.6":{"draws":7,"losses":11,"wins":10},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"losses":5,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":2,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":23,"losses":26,"wins":9},"z-ai/glm-5.3":{"draws":13,"losses":10,"wins":3},"z-ai/glm-5.3-flash":{"draws":17,"losses":16,"wins":1},"z-ai/glm-5.3-flashx":{"draws":0,"losses":7,"wins":1}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":1,"wins":16},"claude-fable-5":{"draws":13,"losses":13,"wins":22},"claude-fable-5-1":{"draws":8,"losses":49,"wins":7},"claude-opus-4-5":{"draws":12,"losses":7,"wins":31},"claude-opus-4-8":{"draws":2,"losses":1,"wins":1},"claude-opus-5":{"draws":9,"losses":23,"wins":6},"claude-opus-5-5":{"draws":0,"losses":2,"wins":4},"claude-sonnet-5":{"draws":18,"losses":5,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":8,"losses":5,"wins":29},"deepseek/deepseek-v4-pro":{"draws":12,"losses":5,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":7,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":2,"wins":12},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":11,"losses":8,"wins":25},"google/gemini-3.5-flash-lite":{"draws":21,"losses":6,"wins":47},"google/gemini-3.6-flash":{"draws":21,"losses":20,"wins":35},"google/gemini-3.8-flash":{"draws":12,"losses":17,"wins":27},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":3},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":5,"wins":6},"gpt-5.4":{"draws":6,"losses":13,"wins":31},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":12},"gpt-5.5":{"draws":6,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":9,"losses":8,"wins":17},"gpt-5.6-sol":{"draws":11,"losses":24,"wins":29},"gpt-5.6-terra":{"draws":16,"losses":8,"wins":20},"gpt-6-astra":{"draws":1,"losses":46,"wins":5},"gpt-6-luna":{"draws":2,"losses":1,"wins":9},"gpt-6-sol":{"draws":0,"losses":4,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":7},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":19},"meituan/longcat-2.0":{"draws":4,"losses":2,"wins":18},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":13},"meta/muse-spark-1.2":{"draws":13,"losses":4,"wins":17},"meta/muse-spark-1.3":{"draws":12,"losses":12,"wins":26},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":0,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":8,"wins":17},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":6},"o3":{"draws":0,"losses":9,"wins":35},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":18},"poolside/laguna-s-2.1":{"draws":11,"losses":0,"wins":9},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":5,"wins":19},"qwen/qwen3.8-27b":{"draws":8,"losses":3,"wins":13},"qwen/qwen3.8-flash":{"draws":9,"losses":9,"wins":18},"qwen/qwen3.8-max":{"draws":12,"losses":9,"wins":25},"qwen/qwen3.8-max-0902":{"draws":1,"losses":0,"wins":7},"stealth/ox-alpha":{"draws":38,"losses":39,"wins":69},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":4,"wins":5},"tencent/hy4-preview":{"draws":12,"losses":16,"wins":14},"thinkingmachines/inkling":{"draws":10,"losses":1,"wins":7},"thinkingmachines/inkling-small":{"draws":12,"losses":3,"wins":19},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":16},"x-ai/grok-4.6":{"draws":14,"losses":15,"wins":23},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":6},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":3,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":1,"wins":4},"z-ai/glm-5.2":{"draws":21,"losses":11,"wins":26},"z-ai/glm-5.3":{"draws":14,"losses":26,"wins":18},"z-ai/glm-5.3-flash":{"draws":8,"losses":13,"wins":31},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":6}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":7,"wins":19},"claude-fable-5":{"draws":3,"losses":20,"wins":13},"claude-fable-5-1":{"draws":1,"losses":38,"wins":1},"claude-opus-4-5":{"draws":5,"losses":10,"wins":19},"claude-opus-4-8":{"draws":0,"losses":4,"wins":6},"claude-opus-5":{"draws":0,"losses":15,"wins":1},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":5,"losses":15,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":3,"losses":17,"wins":24},"deepseek/deepseek-v4-pro":{"draws":1,"losses":12,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":12,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":3,"wins":4},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":12},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":23},"google/gemini-3.5-flash-lite":{"draws":3,"losses":8,"wins":41},"google/gemini-3.6-flash":{"draws":8,"losses":23,"wins":27},"google/gemini-3.8-flash":{"draws":6,"losses":21,"wins":23},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":5},"gpt-4.1":{"draws":0,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":6,"wins":8},"gpt-5.4":{"draws":7,"losses":20,"wins":9},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":8},"gpt-5.5":{"draws":0,"losses":8,"wins":0},"gpt-5.6-luna":{"draws":6,"losses":7,"wins":17},"gpt-5.6-sol":{"draws":5,"losses":23,"wins":16},"gpt-5.6-terra":{"draws":10,"losses":14,"wins":20},"gpt-6-astra":{"draws":0,"losses":42,"wins":0},"gpt-6-luna":{"draws":0,"losses":0,"wins":2},"gpt-6-sol":{"draws":1,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":3,"wins":16},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":14},"meituan/longcat-2.0":{"draws":3,"losses":3,"wins":18},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":22},"meta/muse-spark-1.2":{"draws":2,"losses":5,"wins":19},"meta/muse-spark-1.3":{"draws":4,"losses":10,"wins":20},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":8,"losses":18,"wins":10},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":7},"o3":{"draws":4,"losses":12,"wins":36},"openai/gpt-oss-120b":{"draws":0,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":18},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":1,"losses":3,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":19,"wins":9},"qwen/qwen3.8-27b":{"draws":0,"losses":4,"wins":6},"qwen/qwen3.8-flash":{"draws":5,"losses":4,"wins":13},"qwen/qwen3.8-max":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":6},"stealth/ox-alpha":{"draws":22,"losses":36,"wins":60},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":11},"tencent/hy4-preview":{"draws":4,"losses":12,"wins":12},"thinkingmachines/inkling":{"draws":1,"losses":3,"wins":18},"thinkingmachines/inkling-small":{"draws":4,"losses":1,"wins":33},"x-ai/grok-4.5":{"draws":0,"losses":22,"wins":10},"x-ai/grok-4.6":{"draws":8,"losses":16,"wins":20},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":7,"losses":14,"wins":25},"z-ai/glm-5.3":{"draws":6,"losses":24,"wins":6},"z-ai/glm-5.3-flash":{"draws":6,"losses":12,"wins":24}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":17},"claude-fable-5":{"draws":10,"losses":29,"wins":11},"claude-fable-5-1":{"draws":2,"losses":56,"wins":2},"claude-opus-4-5":{"draws":15,"losses":9,"wins":22},"claude-opus-4-8":{"draws":3,"losses":8,"wins":9},"claude-opus-5":{"draws":1,"losses":22,"wins":5},"claude-opus-5-5":{"draws":2,"losses":6,"wins":0},"claude-sonnet-5":{"draws":6,"losses":14,"wins":28},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":19,"losses":12,"wins":23},"deepseek/deepseek-v4-pro":{"draws":10,"losses":17,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":13,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":5,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":16,"losses":17,"wins":13},"google/gemini-3.5-flash-lite":{"draws":19,"losses":12,"wins":43},"google/gemini-3.6-flash":{"draws":14,"losses":36,"wins":32},"google/gemini-3.8-flash":{"draws":16,"losses":28,"wins":10},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":4,"losses":2,"wins":2},"gpt-5":{"draws":5,"losses":2,"wins":1},"gpt-5.4":{"draws":12,"losses":17,"wins":17},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":6},"gpt-5.5":{"draws":5,"losses":4,"wins":7},"gpt-5.6-luna":{"draws":10,"losses":10,"wins":21},"gpt-5.6-sol":{"draws":12,"losses":32,"wins":8},"gpt-5.6-terra":{"draws":20,"losses":9,"wins":13},"gpt-6-astra":{"draws":7,"losses":43,"wins":0},"gpt-6-luna":{"draws":4,"losses":2,"wins":8},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":11,"losses":0,"wins":15},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":12},"meituan/longcat-2.0":{"draws":7,"losses":2,"wins":19},"meta/muse-glimmer-30b":{"draws":8,"losses":8,"wins":12},"meta/muse-spark-1.2":{"draws":9,"losses":12,"wins":12},"meta/muse-spark-1.3":{"draws":10,"losses":25,"wins":11},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":16,"wins":21},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":10},"o3":{"draws":10,"losses":16,"wins":29},"openai/gpt-oss-120b":{"draws":9,"losses":1,"wins":24},"poolside/laguna-s-2.1":{"draws":16,"losses":3,"wins":11},"qwen/qwen3.7-max":{"draws":9,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":27,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":8,"wins":15},"qwen/qwen3.8-flash":{"draws":11,"losses":6,"wins":11},"qwen/qwen3.8-max":{"draws":15,"losses":17,"wins":23},"qwen/qwen3.8-max-0902":{"draws":4,"losses":6,"wins":2},"stealth/ox-alpha":{"draws":44,"losses":75,"wins":63},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":16},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":9,"losses":19,"wins":18},"thinkingmachines/inkling":{"draws":16,"losses":4,"wins":14},"thinkingmachines/inkling-small":{"draws":32,"losses":15,"wins":39},"x-ai/grok-4.5":{"draws":8,"losses":13,"wins":16},"x-ai/grok-4.6":{"draws":16,"losses":23,"wins":23},"x-ai/grok-4.7":{"draws":2,"losses":0,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":1,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":8,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":21,"losses":17,"wins":14},"z-ai/glm-5.3":{"draws":9,"losses":36,"wins":11},"z-ai/glm-5.3-flash":{"draws":16,"losses":13,"wins":27},"z-ai/glm-5.3-flashx":{"draws":6,"losses":4,"wins":4}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":1,"wins":5},"claude-fable-5":{"draws":3,"losses":2,"wins":1},"claude-fable-5-1":{"draws":2,"losses":4,"wins":4},"claude-opus-4-5":{"draws":2,"losses":0,"wins":8},"claude-opus-4-8":{"draws":3,"losses":1,"wins":4},"claude-opus-5":{"draws":5,"losses":3,"wins":10},"claude-opus-5-5":{"draws":0,"losses":3,"wins":1},"claude-sonnet-5":{"draws":4,"losses":0,"wins":4},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":4,"wins":11},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":1,"losses":3,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":8},"google/gemini-3.8-flash":{"draws":3,"losses":0,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":0,"wins":0},"gpt-5.4":{"draws":0,"losses":1,"wins":5},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":11},"gpt-5.5":{"draws":2,"losses":0,"wins":6},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":9},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":2},"gpt-5.6-terra":{"draws":5,"losses":0,"wins":5},"gpt-6-astra":{"draws":3,"losses":1,"wins":0},"gpt-6-luna":{"draws":6,"losses":0,"wins":6},"gpt-6-sol":{"draws":5,"losses":8,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":3},"inclusionai/ling-3.0-flash":{"draws":3,"losses":0,"wins":7},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":10},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":7},"meta/muse-spark-1.2":{"draws":3,"losses":1,"wins":6},"meta/muse-spark-1.3":{"draws":4,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":10},"moonshotai/kimi-k3":{"draws":6,"losses":2,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":5},"o3":{"draws":3,"losses":0,"wins":5},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":11},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":5,"wins":6},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.8-max-0902":{"draws":5,"losses":3,"wins":18},"stealth/ox-alpha":{"draws":6,"losses":2,"wins":16},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":1},"tencent/hy4-preview":{"draws":1,"losses":2,"wins":5},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":3},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":6},"x-ai/grok-4.6":{"draws":1,"losses":3,"wins":8},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":12},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":1,"wins":5},"z-ai/glm-5.2":{"draws":2,"losses":0,"wins":12},"z-ai/glm-5.3":{"draws":3,"losses":3,"wins":4},"z-ai/glm-5.3-flash":{"draws":0,"losses":2,"wins":4},"z-ai/glm-5.3-flashx":{"draws":4,"losses":4,"wins":20}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":17,"wins":68},"claude-fable-5":{"draws":20,"losses":97,"wins":49},"claude-fable-5-1":{"draws":24,"losses":155,"wins":21},"claude-opus-4-5":{"draws":24,"losses":35,"wins":104},"claude-opus-4-8":{"draws":7,"losses":12,"wins":29},"claude-opus-5":{"draws":15,"losses":77,"wins":13},"claude-opus-5-5":{"draws":2,"losses":25,"wins":3},"claude-sonnet-5":{"draws":17,"losses":38,"wins":86},"cohere/north-mini-code":{"draws":0,"losses":5,"wins":13},"deepseek/deepseek-v4-flash":{"draws":8,"losses":10,"wins":95},"deepseek/deepseek-v4-pro":{"draws":18,"losses":27,"wins":65},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":30,"wins":73},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":7,"wins":21},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":19,"losses":52,"wins":88},"google/gemini-3.5-flash-lite":{"draws":21,"losses":21,"wins":143},"google/gemini-3.6-flash":{"draws":25,"losses":82,"wins":118},"google/gemini-3.8-flash":{"draws":23,"losses":60,"wins":85},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":10},"gpt-4.1":{"draws":3,"losses":5,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":8},"gpt-5":{"draws":2,"losses":6,"wins":16},"gpt-5.4":{"draws":28,"losses":47,"wins":68},"gpt-5.4-mini":{"draws":4,"losses":5,"wins":19},"gpt-5.4-nano":{"draws":1,"losses":7,"wins":30},"gpt-5.5":{"draws":6,"losses":8,"wins":20},"gpt-5.6-luna":{"draws":23,"losses":21,"wins":65},"gpt-5.6-sol":{"draws":22,"losses":85,"wins":80},"gpt-5.6-terra":{"draws":24,"losses":39,"wins":67},"gpt-6-astra":{"draws":34,"losses":134,"wins":26},"gpt-6-luna":{"draws":2,"losses":2,"wins":12},"gpt-6-sol":{"draws":1,"losses":10,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":7,"losses":9,"wins":39},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":28},"meituan/longcat-2.0":{"draws":10,"losses":18,"wins":51},"meta/muse-glimmer-30b":{"draws":5,"losses":2,"wins":63},"meta/muse-spark-1.2":{"draws":19,"losses":19,"wins":79},"meta/muse-spark-1.3":{"draws":20,"losses":52,"wins":77},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":12},"mistralai/mistral-medium-3-5":{"draws":9,"losses":7,"wins":30},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k3":{"draws":24,"losses":31,"wins":86},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":16},"o3":{"draws":5,"losses":40,"wins":93},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":62},"poolside/laguna-s-2.1":{"draws":15,"losses":6,"wins":52},"qwen/qwen3.7-max":{"draws":1,"losses":6,"wins":27},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":44,"wins":82},"qwen/qwen3.8-27b":{"draws":10,"losses":22,"wins":53},"qwen/qwen3.8-flash":{"draws":17,"losses":26,"wins":56},"qwen/qwen3.8-max":{"draws":21,"losses":42,"wins":103},"qwen/qwen3.8-max-0902":{"draws":8,"losses":9,"wins":19},"stealth/ox-alpha":{"draws":88,"losses":123,"wins":310},"stepfun/step-3.7-flash":{"draws":3,"losses":3,"wins":26},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":6},"tencent/hy4-preview":{"draws":20,"losses":51,"wins":72},"thinkingmachines/inkling":{"draws":10,"losses":17,"wins":76},"thinkingmachines/inkling-small":{"draws":14,"losses":3,"wins":93},"x-ai/grok-4.5":{"draws":10,"losses":53,"wins":45},"x-ai/grok-4.6":{"draws":28,"losses":69,"wins":73},"x-ai/grok-4.7":{"draws":2,"losses":9,"wins":1},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":7,"losses":2,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":8,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":5,"wins":8},"z-ai/glm-5.2":{"draws":23,"losses":33,"wins":100},"z-ai/glm-5.3":{"draws":18,"losses":78,"wins":64},"z-ai/glm-5.3-flash":{"draws":21,"losses":49,"wins":83},"z-ai/glm-5.3-flashx":{"draws":6,"losses":10,"wins":18}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":11,"wins":1},"claude-fable-5":{"draws":0,"losses":11,"wins":1},"claude-fable-5-1":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":5,"losses":31,"wins":8},"claude-opus-4-8":{"draws":2,"losses":18,"wins":6},"claude-opus-5":{"draws":0,"losses":26,"wins":0},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":2,"losses":7,"wins":3},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":6,"losses":8,"wins":14},"deepseek/deepseek-v4-pro":{"draws":4,"losses":3,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":1,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":3,"wins":20},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":5},"google/gemini-3.5-flash-lite":{"draws":10,"losses":12,"wins":6},"google/gemini-3.6-flash":{"draws":6,"losses":20,"wins":3},"google/gemini-3.8-flash":{"draws":4,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":2,"losses":6,"wins":2},"gpt-5":{"draws":12,"losses":26,"wins":2},"gpt-5.4":{"draws":5,"losses":10,"wins":5},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":3},"gpt-5.4-nano":{"draws":4,"losses":16,"wins":14},"gpt-5.5":{"draws":3,"losses":28,"wins":5},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":1,"losses":3,"wins":2},"gpt-6-sol":{"draws":0,"losses":9,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":7},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":6},"meta/muse-glimmer-30b":{"draws":0,"losses":6,"wins":2},"meta/muse-spark-1.2":{"draws":0,"losses":9,"wins":1},"meta/muse-spark-1.3":{"draws":0,"losses":14,"wins":0},"minimax/minimax-m3":{"draws":3,"losses":9,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":10,"wins":2},"nex-agi/nex-n2-pro":{"draws":6,"losses":10,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":12,"wins":16},"o3":{"draws":13,"losses":33,"wins":16},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":2,"losses":2,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":9,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":16,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":6,"wins":0},"qwen/qwen3.8-27b":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.8-max":{"draws":1,"losses":9,"wins":0},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":2},"stealth/ox-alpha":{"draws":5,"losses":22,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":6,"wins":0},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":0,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":5,"losses":9,"wins":24},"thinkingmachines/inkling-small":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":17,"wins":3},"x-ai/grok-4.6":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":24,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":10,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":20,"wins":10},"z-ai/glm-5.3":{"draws":0,"losses":10,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":4,"wins":0},"z-ai/glm-5.3-flashx":{"draws":0,"losses":1,"wins":1}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":3,"wins":5},"claude-fable-5":{"draws":2,"losses":6,"wins":0},"claude-fable-5-1":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":23,"losses":27,"wins":12},"claude-opus-4-8":{"draws":7,"losses":17,"wins":8},"claude-opus-5":{"draws":6,"losses":64,"wins":4},"claude-opus-5-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":6,"losses":8,"wins":6},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":10,"losses":12,"wins":12},"deepseek/deepseek-v4-pro":{"draws":5,"losses":3,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":4,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":12,"losses":10,"wins":12},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":7,"losses":6,"wins":7},"google/gemini-3.6-flash":{"draws":10,"losses":18,"wins":12},"google/gemini-3.8-flash":{"draws":4,"losses":7,"wins":1},"google/gemma-4-31b-it":{"draws":6,"losses":7,"wins":11},"gpt-4.1":{"draws":12,"losses":8,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":18,"losses":23,"wins":21},"gpt-5.4":{"draws":4,"losses":7,"wins":9},"gpt-5.4-mini":{"draws":8,"losses":8,"wins":6},"gpt-5.4-nano":{"draws":4,"losses":5,"wins":13},"gpt-5.5":{"draws":22,"losses":19,"wins":7},"gpt-5.6-luna":{"draws":0,"losses":6,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":1,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":5,"wins":4},"gpt-6-astra":{"draws":0,"losses":8,"wins":0},"gpt-6-luna":{"draws":7,"losses":3,"wins":4},"gpt-6-sol":{"draws":1,"losses":9,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":6,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":7,"losses":13,"wins":14},"meta/muse-glimmer-30b":{"draws":5,"losses":3,"wins":8},"meta/muse-spark-1.2":{"draws":2,"losses":10,"wins":4},"meta/muse-spark-1.3":{"draws":2,"losses":9,"wins":3},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":11},"mistralai/mistral-medium-3-5":{"draws":5,"losses":1,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":4,"wins":6},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":2},"nex-agi/nex-n2-pro":{"draws":10,"losses":4,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":29,"losses":10,"wins":19},"o3":{"draws":13,"losses":13,"wins":20},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":3,"losses":7,"wins":10},"qwen/qwen3.7-max":{"draws":11,"losses":18,"wins":5},"qwen/qwen3.7-plus":{"draws":8,"losses":8,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":6,"wins":4},"qwen/qwen3.8-27b":{"draws":5,"losses":6,"wins":3},"qwen/qwen3.8-flash":{"draws":6,"losses":2,"wins":4},"qwen/qwen3.8-max":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.8-max-0902":{"draws":3,"losses":4,"wins":5},"stealth/ox-alpha":{"draws":17,"losses":15,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":7,"wins":7},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":3},"tencent/hy4-preview":{"draws":4,"losses":10,"wins":4},"thinkingmachines/inkling":{"draws":14,"losses":8,"wins":8},"thinkingmachines/inkling-small":{"draws":13,"losses":4,"wins":13},"x-ai/grok-4.5":{"draws":4,"losses":22,"wins":2},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":5},"xiaomi/mimo-v2.5":{"draws":19,"losses":17,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":11,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":6,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":14,"wins":17},"z-ai/glm-5.3":{"draws":1,"losses":3,"wins":2},"z-ai/glm-5.3-flash":{"draws":1,"losses":11,"wins":0},"z-ai/glm-5.3-flashx":{"draws":1,"losses":2,"wins":5}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":4,"wins":15},"claude-fable-5":{"draws":13,"losses":26,"wins":17},"claude-fable-5-1":{"draws":3,"losses":53,"wins":10},"claude-opus-4-5":{"draws":17,"losses":14,"wins":31},"claude-opus-4-8":{"draws":5,"losses":6,"wins":13},"claude-opus-5":{"draws":4,"losses":37,"wins":1},"claude-opus-5-5":{"draws":0,"losses":7,"wins":1},"claude-sonnet-5":{"draws":16,"losses":6,"wins":22},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":12,"losses":2,"wins":24},"deepseek/deepseek-v4-pro":{"draws":14,"losses":10,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":6,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":12,"losses":8,"wins":38},"google/gemini-3.5-flash-lite":{"draws":31,"losses":5,"wins":28},"google/gemini-3.6-flash":{"draws":21,"losses":25,"wins":38},"google/gemini-3.8-flash":{"draws":9,"losses":14,"wins":21},"gpt-4.1":{"draws":0,"losses":0,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":10,"losses":0,"wins":2},"gpt-5.4":{"draws":11,"losses":15,"wins":16},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":11},"gpt-5.5":{"draws":1,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":17,"losses":7,"wins":20},"gpt-5.6-sol":{"draws":10,"losses":31,"wins":25},"gpt-5.6-terra":{"draws":17,"losses":7,"wins":24},"gpt-6-astra":{"draws":7,"losses":49,"wins":8},"gpt-6-luna":{"draws":2,"losses":1,"wins":1},"gpt-6-sol":{"draws":2,"losses":4,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":1,"wins":6},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":3,"losses":4,"wins":9},"meta/muse-glimmer-30b":{"draws":17,"losses":0,"wins":11},"meta/muse-spark-1.2":{"draws":4,"losses":12,"wins":22},"meta/muse-spark-1.3":{"draws":8,"losses":14,"wins":22},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":9,"losses":0,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":11,"losses":12,"wins":19},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":1,"wins":3},"o3":{"draws":11,"losses":15,"wins":24},"openai/gpt-oss-120b":{"draws":13,"losses":2,"wins":1},"poolside/laguna-s-2.1":{"draws":18,"losses":5,"wins":9},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":6},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":13,"wins":28},"qwen/qwen3.8-27b":{"draws":9,"losses":5,"wins":14},"qwen/qwen3.8-flash":{"draws":9,"losses":12,"wins":11},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":24},"qwen/qwen3.8-max-0902":{"draws":0,"losses":0,"wins":4},"stealth/ox-alpha":{"draws":46,"losses":35,"wins":91},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":5,"losses":6,"wins":11},"thinkingmachines/inkling":{"draws":15,"losses":3,"wins":16},"thinkingmachines/inkling-small":{"draws":16,"losses":2,"wins":20},"x-ai/grok-4.5":{"draws":6,"losses":14,"wins":26},"x-ai/grok-4.6":{"draws":19,"losses":17,"wins":20},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":20,"losses":5,"wins":33},"z-ai/glm-5.3":{"draws":7,"losses":33,"wins":12},"z-ai/glm-5.3-flash":{"draws":16,"losses":22,"wins":14},"z-ai/glm-5.3-flashx":{"draws":1,"losses":1,"wins":4}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":28,"wins":18},"claude-fable-5":{"draws":12,"losses":34,"wins":0},"claude-fable-5-1":{"draws":4,"losses":34,"wins":0},"claude-opus-4-5":{"draws":34,"losses":70,"wins":18},"claude-opus-4-8":{"draws":9,"losses":21,"wins":2},"claude-opus-5":{"draws":1,"losses":33,"wins":2},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":31,"losses":68,"wins":15},"cohere/north-mini-code":{"draws":5,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":27,"losses":23,"wins":12},"deepseek/deepseek-v4-pro":{"draws":23,"losses":23,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":23,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":4,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":7,"wins":14},"google/gemini-3.5-flash":{"draws":23,"losses":27,"wins":16},"google/gemini-3.5-flash-lite":{"draws":96,"losses":104,"wins":82},"google/gemini-3.6-flash":{"draws":69,"losses":132,"wins":33},"google/gemini-3.8-flash":{"draws":17,"losses":20,"wins":3},"gpt-4.1":{"draws":3,"losses":3,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":5,"losses":13,"wins":14},"gpt-5.4":{"draws":21,"losses":45,"wins":16},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":7,"losses":4,"wins":1},"gpt-5.5":{"draws":11,"losses":13,"wins":4},"gpt-5.6-luna":{"draws":47,"losses":46,"wins":21},"gpt-5.6-sol":{"draws":22,"losses":69,"wins":9},"gpt-5.6-terra":{"draws":21,"losses":31,"wins":8},"gpt-6-astra":{"draws":3,"losses":35,"wins":0},"gpt-6-luna":{"draws":3,"losses":8,"wins":1},"gpt-6-sol":{"draws":1,"losses":12,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":24,"losses":8,"wins":14},"inclusionai/ling-3.0-flash":{"draws":30,"losses":12,"wins":12},"meituan/longcat-2.0":{"draws":21,"losses":26,"wins":49},"meta/muse-glimmer-30b":{"draws":20,"losses":18,"wins":16},"meta/muse-spark-1.2":{"draws":27,"losses":41,"wins":6},"meta/muse-spark-1.3":{"draws":14,"losses":20,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":5,"wins":2},"mistralai/mistral-medium-3-5":{"draws":11,"losses":10,"wins":19},"moonshotai/kimi-k3":{"draws":53,"losses":53,"wins":14},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":14,"wins":5},"o3":{"draws":30,"losses":94,"wins":40},"openai/gpt-oss-120b":{"draws":16,"losses":15,"wins":23},"poolside/laguna-s-2.1":{"draws":38,"losses":37,"wins":23},"qwen/qwen3.7-max":{"draws":6,"losses":8,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":19,"wins":5},"qwen/qwen3.8-27b":{"draws":9,"losses":22,"wins":5},"qwen/qwen3.8-flash":{"draws":13,"losses":17,"wins":8},"qwen/qwen3.8-max":{"draws":16,"losses":22,"wins":16},"qwen/qwen3.8-max-0902":{"draws":0,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":51,"losses":98,"wins":27},"stepfun/step-3.7-flash":{"draws":12,"losses":15,"wins":19},"tencent/hy3-preview":{"draws":3,"losses":6,"wins":5},"tencent/hy4-preview":{"draws":22,"losses":27,"wins":9},"thinkingmachines/inkling":{"draws":14,"losses":29,"wins":13},"thinkingmachines/inkling-small":{"draws":23,"losses":10,"wins":25},"x-ai/grok-4.5":{"draws":31,"losses":52,"wins":13},"x-ai/grok-4.6":{"draws":15,"losses":16,"wins":5},"x-ai/grok-4.7":{"draws":3,"losses":0,"wins":1},"x-ai/grok-build-0.1":{"draws":9,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":2,"losses":5,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":5,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":27,"losses":29,"wins":22},"z-ai/glm-5.3":{"draws":11,"losses":20,"wins":3},"z-ai/glm-5.3-flash":{"draws":17,"losses":30,"wins":9},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":0}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":21,"wins":10},"claude-fable-5":{"draws":7,"losses":29,"wins":4},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-opus-4-5":{"draws":19,"losses":21,"wins":14},"claude-opus-4-8":{"draws":8,"losses":6,"wins":0},"claude-opus-5":{"draws":0,"losses":31,"wins":1},"claude-opus-5-5":{"draws":2,"losses":6,"wins":0},"claude-sonnet-5":{"draws":12,"losses":30,"wins":10},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":19,"losses":23,"wins":12},"deepseek/deepseek-v4-pro":{"draws":19,"losses":16,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":23,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":6,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":7},"google/gemini-3.5-flash":{"draws":11,"losses":30,"wins":11},"google/gemini-3.5-flash-lite":{"draws":30,"losses":22,"wins":51},"google/gemini-3.6-flash":{"draws":28,"losses":28,"wins":13},"google/gemini-3.8-flash":{"draws":15,"losses":26,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":1,"losses":10,"wins":1},"gpt-5.4":{"draws":12,"losses":22,"wins":5},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":9,"losses":3,"wins":10},"gpt-5.5":{"draws":2,"losses":6,"wins":0},"gpt-5.6-luna":{"draws":27,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":8,"losses":32,"wins":7},"gpt-5.6-terra":{"draws":14,"losses":22,"wins":12},"gpt-6-astra":{"draws":5,"losses":39,"wins":0},"gpt-6-luna":{"draws":1,"losses":3,"wins":0},"gpt-6-sol":{"draws":1,"losses":10,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":22,"losses":7,"wins":15},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":13},"meituan/longcat-2.0":{"draws":16,"losses":6,"wins":16},"meta/muse-glimmer-30b":{"draws":22,"losses":13,"wins":11},"meta/muse-spark-1.2":{"draws":14,"losses":18,"wins":6},"meta/muse-spark-1.3":{"draws":17,"losses":26,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":4,"wins":4},"mistralai/mistral-medium-3-5":{"draws":16,"losses":2,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":19,"wins":6},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":5},"o3":{"draws":21,"losses":21,"wins":20},"openai/gpt-oss-120b":{"draws":21,"losses":16,"wins":17},"poolside/laguna-s-2.1":{"draws":16,"losses":11,"wins":13},"qwen/qwen3.7-max":{"draws":3,"losses":6,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":20,"wins":8},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":7},"qwen/qwen3.8-flash":{"draws":15,"losses":7,"wins":10},"qwen/qwen3.8-max":{"draws":32,"losses":25,"wins":30},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":50,"losses":92,"wins":26},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":7},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":4},"tencent/hy4-preview":{"draws":20,"losses":26,"wins":6},"thinkingmachines/inkling":{"draws":15,"losses":9,"wins":12},"thinkingmachines/inkling-small":{"draws":25,"losses":10,"wins":29},"x-ai/grok-4.5":{"draws":7,"losses":17,"wins":12},"x-ai/grok-4.6":{"draws":19,"losses":19,"wins":8},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":5,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":30,"losses":21,"wins":15},"z-ai/glm-5.3":{"draws":12,"losses":29,"wins":5},"z-ai/glm-5.3-flash":{"draws":24,"losses":26,"wins":8},"z-ai/glm-5.3-flashx":{"draws":2,"losses":1,"wins":1}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":1,"wins":34},"claude-fable-5":{"draws":4,"losses":17,"wins":25},"claude-fable-5-1":{"draws":1,"losses":50,"wins":5},"claude-opus-4-5":{"draws":31,"losses":20,"wins":63},"claude-opus-4-8":{"draws":6,"losses":12,"wins":8},"claude-opus-5":{"draws":9,"losses":50,"wins":15},"claude-opus-5-5":{"draws":1,"losses":4,"wins":3},"claude-sonnet-5":{"draws":20,"losses":25,"wins":57},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":7,"losses":10,"wins":29},"deepseek/deepseek-v4-pro":{"draws":10,"losses":11,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":12,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":16},"google/gemini-3.5-flash":{"draws":7,"losses":15,"wins":20},"google/gemini-3.5-flash-lite":{"draws":28,"losses":52,"wins":118},"google/gemini-3.6-flash":{"draws":25,"losses":79,"wins":102},"google/gemini-3.8-flash":{"draws":7,"losses":16,"wins":29},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":4,"wins":14},"gpt-5.4":{"draws":24,"losses":36,"wins":41},"gpt-5.4-mini":{"draws":1,"losses":1,"wins":6},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":5},"gpt-5.5":{"draws":5,"losses":7,"wins":6},"gpt-5.6-luna":{"draws":17,"losses":33,"wins":44},"gpt-5.6-sol":{"draws":14,"losses":43,"wins":39},"gpt-5.6-terra":{"draws":14,"losses":7,"wins":41},"gpt-6-astra":{"draws":0,"losses":44,"wins":8},"gpt-6-sol":{"draws":1,"losses":1,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":19},"inclusionai/ling-3.0-flash":{"draws":8,"losses":8,"wins":34},"meituan/longcat-2.0":{"draws":27,"losses":7,"wins":52},"meta/muse-glimmer-30b":{"draws":8,"losses":6,"wins":24},"meta/muse-spark-1.2":{"draws":11,"losses":14,"wins":41},"meta/muse-spark-1.3":{"draws":4,"losses":14,"wins":24},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":5},"mistralai/mistral-medium-3-5":{"draws":10,"losses":2,"wins":14},"moonshotai/kimi-k3":{"draws":32,"losses":30,"wins":70},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":0,"wins":19},"o3":{"draws":9,"losses":22,"wins":93},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":24},"poolside/laguna-s-2.1":{"draws":24,"losses":10,"wins":54},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":11},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":13,"wins":26},"qwen/qwen3.8-27b":{"draws":0,"losses":6,"wins":16},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":15},"qwen/qwen3.8-max":{"draws":8,"losses":14,"wins":22},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":30,"losses":34,"wins":82},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":20},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":19},"tencent/hy4-preview":{"draws":7,"losses":14,"wins":25},"thinkingmachines/inkling":{"draws":26,"losses":13,"wins":47},"thinkingmachines/inkling-small":{"draws":5,"losses":10,"wins":25},"x-ai/grok-4.5":{"draws":24,"losses":10,"wins":28},"x-ai/grok-4.6":{"draws":7,"losses":19,"wins":28},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":11,"wins":31},"z-ai/glm-5.3":{"draws":14,"losses":25,"wins":13},"z-ai/glm-5.3-flash":{"draws":8,"losses":17,"wins":15},"z-ai/glm-5.3-flashx":{"draws":0,"losses":5,"wins":1}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":9,"wins":10},"claude-fable-5":{"draws":18,"losses":21,"wins":25},"claude-fable-5-1":{"draws":4,"losses":49,"wins":13},"claude-opus-4-5":{"draws":13,"losses":7,"wins":30},"claude-opus-4-8":{"draws":1,"losses":11,"wins":8},"claude-opus-5":{"draws":4,"losses":14,"wins":7},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":9,"losses":5,"wins":26},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":20,"losses":5,"wins":29},"deepseek/deepseek-v4-pro":{"draws":11,"losses":14,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":15,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":4,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":14,"losses":8,"wins":26},"google/gemini-3.5-flash-lite":{"draws":25,"losses":9,"wins":46},"google/gemini-3.6-flash":{"draws":16,"losses":26,"wins":32},"google/gemini-3.8-flash":{"draws":16,"losses":16,"wins":22},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-4.1":{"draws":2,"losses":1,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":2,"wins":6},"gpt-5.4":{"draws":15,"losses":17,"wins":20},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":12},"gpt-5.4-nano":{"draws":5,"losses":3,"wins":10},"gpt-5.5":{"draws":7,"losses":2,"wins":9},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":25},"gpt-5.6-sol":{"draws":8,"losses":19,"wins":33},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":40},"gpt-6-astra":{"draws":5,"losses":49,"wins":8},"gpt-6-sol":{"draws":1,"losses":7,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":7},"inclusionai/ling-3.0-flash":{"draws":8,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":7,"losses":1,"wins":18},"meta/muse-glimmer-30b":{"draws":12,"losses":9,"wins":11},"meta/muse-spark-1.2":{"draws":5,"losses":10,"wins":21},"meta/muse-spark-1.3":{"draws":7,"losses":15,"wins":22},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":8,"wins":20},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":2},"o3":{"draws":10,"losses":12,"wins":22},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":11},"poolside/laguna-s-2.1":{"draws":8,"losses":2,"wins":18},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":4},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":18,"wins":24},"qwen/qwen3.8-27b":{"draws":6,"losses":8,"wins":10},"qwen/qwen3.8-flash":{"draws":13,"losses":6,"wins":15},"qwen/qwen3.8-max":{"draws":6,"losses":20,"wins":26},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":6},"stealth/ox-alpha":{"draws":53,"losses":50,"wins":71},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":5},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":16,"losses":12,"wins":20},"thinkingmachines/inkling":{"draws":10,"losses":5,"wins":5},"thinkingmachines/inkling-small":{"draws":20,"losses":6,"wins":16},"x-ai/grok-4.5":{"draws":11,"losses":13,"wins":16},"x-ai/grok-4.6":{"draws":17,"losses":6,"wins":19},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":5,"losses":1,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":13,"losses":11,"wins":34},"z-ai/glm-5.3":{"draws":11,"losses":24,"wins":21},"z-ai/glm-5.3-flash":{"draws":13,"losses":18,"wins":17},"z-ai/glm-5.3-flashx":{"draws":4,"losses":0,"wins":2}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":4},"claude-fable-5":{"draws":1,"losses":1,"wins":4},"claude-fable-5-1":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":0,"losses":0,"wins":2},"claude-opus-4-8":{"draws":0,"losses":1,"wins":1},"claude-opus-5":{"draws":0,"losses":2,"wins":0},"claude-opus-5-5":{"draws":0,"losses":13,"wins":9},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":6},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":2,"losses":0,"wins":8},"google/gemini-3.8-flash":{"draws":0,"losses":1,"wins":5},"gpt-5":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":0,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.5":{"draws":0,"losses":3,"wins":5},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":1},"gpt-6-astra":{"draws":0,"losses":1,"wins":3},"gpt-6-luna":{"draws":0,"losses":1,"wins":15},"gpt-6-sol":{"draws":0,"losses":7,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":4},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":3,"losses":1,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":1,"wins":7},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.8-max-0902":{"draws":0,"losses":0,"wins":8},"stealth/ox-alpha":{"draws":3,"losses":2,"wins":9},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":0,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":4},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":6},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":1,"wins":5},"z-ai/glm-5.3":{"draws":0,"losses":1,"wins":3},"z-ai/glm-5.3-flash":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.3-flashx":{"draws":2,"losses":2,"wins":6}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":2,"wins":0},"claude-fable-5":{"draws":4,"losses":8,"wins":0},"claude-fable-5-1":{"draws":0,"losses":12,"wins":0},"claude-opus-4-5":{"draws":33,"losses":12,"wins":3},"claude-opus-4-8":{"draws":11,"losses":8,"wins":3},"claude-opus-5":{"draws":7,"losses":25,"wins":2},"claude-opus-5-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":10,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":19,"losses":1,"wins":4},"deepseek/deepseek-v4-pro":{"draws":8,"losses":4,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":4,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":17,"losses":2,"wins":1},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":4},"google/gemini-3.5-flash-lite":{"draws":10,"losses":3,"wins":1},"google/gemini-3.6-flash":{"draws":13,"losses":8,"wins":5},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":0},"google/gemma-4-31b-it":{"draws":8,"losses":0,"wins":0},"gpt-4.1":{"draws":10,"losses":4,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":25,"losses":4,"wins":5},"gpt-5.4-mini":{"draws":23,"losses":0,"wins":9},"gpt-5.4-nano":{"draws":18,"losses":16,"wins":8},"gpt-5.5":{"draws":8,"losses":13,"wins":5},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":0},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":0},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"gpt-6-luna":{"draws":5,"losses":5,"wins":2},"gpt-6-sol":{"draws":1,"losses":5,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":16,"losses":0,"wins":0},"meituan/longcat-2.0":{"draws":10,"losses":6,"wins":2},"meta/muse-glimmer-30b":{"draws":10,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":0,"wins":4},"meta/muse-spark-1.3":{"draws":4,"losses":10,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":9,"wins":0},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":3,"wins":0},"nex-agi/nex-n2-pro":{"draws":12,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":2,"wins":4},"o3":{"draws":9,"losses":5,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":16,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":13,"losses":7,"wins":0},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":6,"losses":4,"wins":0},"qwen/qwen3.8-max-0902":{"draws":5,"losses":0,"wins":1},"stealth/ox-alpha":{"draws":16,"losses":14,"wins":4},"stepfun/step-3.7-flash":{"draws":10,"losses":5,"wins":9},"tencent/hy3-preview":{"draws":9,"losses":0,"wins":1},"tencent/hy4-preview":{"draws":4,"losses":6,"wins":0},"thinkingmachines/inkling":{"draws":18,"losses":0,"wins":6},"thinkingmachines/inkling-small":{"draws":9,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":3},"x-ai/grok-4.6":{"draws":7,"losses":5,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":18,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":28,"losses":24,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":0},"z-ai/glm-5.2":{"draws":27,"losses":9,"wins":8},"z-ai/glm-5.3":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":0}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":14,"wins":11},"claude-fable-5":{"draws":9,"losses":19,"wins":10},"claude-fable-5-1":{"draws":3,"losses":29,"wins":0},"claude-opus-4-5":{"draws":9,"losses":23,"wins":10},"claude-opus-4-8":{"draws":7,"losses":6,"wins":3},"claude-opus-5":{"draws":6,"losses":18,"wins":4},"claude-opus-5-5":{"draws":0,"losses":9,"wins":1},"claude-sonnet-5":{"draws":14,"losses":23,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":20,"losses":16,"wins":24},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":19,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":6,"wins":4},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":15,"losses":24,"wins":13},"google/gemini-3.5-flash-lite":{"draws":28,"losses":14,"wins":28},"google/gemini-3.6-flash":{"draws":16,"losses":37,"wins":17},"google/gemini-3.8-flash":{"draws":11,"losses":22,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":6,"losses":7,"wins":3},"gpt-5.4":{"draws":14,"losses":23,"wins":5},"gpt-5.4-mini":{"draws":1,"losses":2,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":8,"wins":2},"gpt-5.5":{"draws":0,"losses":9,"wins":1},"gpt-5.6-luna":{"draws":16,"losses":10,"wins":16},"gpt-5.6-sol":{"draws":5,"losses":33,"wins":6},"gpt-5.6-terra":{"draws":25,"losses":24,"wins":3},"gpt-6-astra":{"draws":4,"losses":34,"wins":0},"gpt-6-luna":{"draws":1,"losses":1,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":2,"wins":4},"inception/mercury-2.5-preview":{"draws":14,"losses":10,"wins":14},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":7,"losses":13,"wins":4},"meta/muse-glimmer-30b":{"draws":19,"losses":9,"wins":16},"meta/muse-spark-1.2":{"draws":6,"losses":13,"wins":9},"meta/muse-spark-1.3":{"draws":9,"losses":18,"wins":9},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":11,"losses":8,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":18,"losses":16,"wins":6},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":2,"wins":9},"o3":{"draws":13,"losses":28,"wins":13},"openai/gpt-oss-120b":{"draws":18,"losses":7,"wins":27},"poolside/laguna-s-2.1":{"draws":13,"losses":3,"wins":14},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":12,"wins":15},"qwen/qwen3.8-27b":{"draws":9,"losses":10,"wins":7},"qwen/qwen3.8-flash":{"draws":13,"losses":13,"wins":6},"qwen/qwen3.8-max":{"draws":18,"losses":12,"wins":10},"qwen/qwen3.8-max-0902":{"draws":1,"losses":6,"wins":1},"stealth/ox-alpha":{"draws":45,"losses":70,"wins":33},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":7,"wins":2},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":8},"thinkingmachines/inkling":{"draws":11,"losses":17,"wins":12},"thinkingmachines/inkling-small":{"draws":18,"losses":11,"wins":23},"x-ai/grok-4.5":{"draws":9,"losses":14,"wins":7},"x-ai/grok-4.6":{"draws":13,"losses":15,"wins":10},"x-ai/grok-4.7":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":5,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":2,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":19,"losses":11,"wins":20},"z-ai/glm-5.3":{"draws":15,"losses":10,"wins":11},"z-ai/glm-5.3-flash":{"draws":13,"losses":19,"wins":6},"z-ai/glm-5.3-flashx":{"draws":3,"losses":4,"wins":3}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":24},"claude-fable-5":{"draws":5,"losses":7,"wins":34},"claude-fable-5-1":{"draws":4,"losses":36,"wins":12},"claude-opus-4-5":{"draws":6,"losses":1,"wins":43},"claude-opus-4-8":{"draws":3,"losses":1,"wins":4},"claude-opus-5":{"draws":6,"losses":8,"wins":12},"claude-opus-5-5":{"draws":0,"losses":5,"wins":3},"claude-sonnet-5":{"draws":3,"losses":0,"wins":41},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":31},"deepseek/deepseek-v4-pro":{"draws":3,"losses":0,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":0,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":1,"wins":6},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash-lite":{"draws":5,"losses":0,"wins":55},"google/gemini-3.6-flash":{"draws":3,"losses":3,"wins":62},"google/gemini-3.8-flash":{"draws":2,"losses":3,"wins":39},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":0,"wins":4},"gpt-5.4":{"draws":5,"losses":5,"wins":32},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":14},"gpt-5.4-nano":{"draws":3,"losses":0,"wins":15},"gpt-5.5":{"draws":0,"losses":2,"wins":4},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":29},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":36},"gpt-5.6-terra":{"draws":6,"losses":1,"wins":35},"gpt-6-astra":{"draws":6,"losses":34,"wins":8},"gpt-6-luna":{"draws":0,"losses":0,"wins":8},"gpt-6-sol":{"draws":3,"losses":3,"wins":10},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":8},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":4,"losses":0,"wins":16},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":9},"meta/muse-spark-1.2":{"draws":4,"losses":0,"wins":24},"meta/muse-spark-1.3":{"draws":4,"losses":1,"wins":37},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":5,"losses":2,"wins":29},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":12},"o3":{"draws":0,"losses":0,"wins":42},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":8},"poolside/laguna-s-2.1":{"draws":6,"losses":0,"wins":18},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":3,"wins":31},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":18},"qwen/qwen3.8-flash":{"draws":1,"losses":1,"wins":30},"qwen/qwen3.8-max":{"draws":4,"losses":1,"wins":31},"qwen/qwen3.8-max-0902":{"draws":1,"losses":0,"wins":5},"stealth/ox-alpha":{"draws":20,"losses":12,"wins":98},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":5},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":41},"thinkingmachines/inkling":{"draws":0,"losses":1,"wins":21},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":21},"x-ai/grok-4.5":{"draws":10,"losses":3,"wins":23},"x-ai/grok-4.6":{"draws":6,"losses":6,"wins":40},"x-ai/grok-4.7":{"draws":3,"losses":2,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":0,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":8},"z-ai/glm-5.2":{"draws":7,"losses":0,"wins":37},"z-ai/glm-5.3":{"draws":6,"losses":1,"wins":25},"z-ai/glm-5.3-flash":{"draws":5,"losses":1,"wins":32},"z-ai/glm-5.3-flashx":{"draws":0,"losses":0,"wins":18}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":6,"wins":18},"claude-fable-5":{"draws":9,"losses":19,"wins":22},"claude-fable-5-1":{"draws":7,"losses":35,"wins":8},"claude-opus-4-5":{"draws":10,"losses":9,"wins":27},"claude-opus-4-8":{"draws":2,"losses":7,"wins":11},"claude-opus-5":{"draws":2,"losses":25,"wins":7},"claude-opus-5-5":{"draws":3,"losses":12,"wins":1},"claude-sonnet-5":{"draws":7,"losses":13,"wins":24},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":7,"losses":11,"wins":18},"deepseek/deepseek-v4-pro":{"draws":8,"losses":11,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":8,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":3,"wins":3},"google/gemini-3.5-flash":{"draws":16,"losses":17,"wins":15},"google/gemini-3.5-flash-lite":{"draws":20,"losses":11,"wins":39},"google/gemini-3.6-flash":{"draws":11,"losses":17,"wins":40},"google/gemini-3.8-flash":{"draws":9,"losses":20,"wins":21},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":7},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":2,"wins":4},"gpt-5.4":{"draws":7,"losses":18,"wins":17},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":8},"gpt-5.5":{"draws":0,"losses":5,"wins":9},"gpt-5.6-luna":{"draws":7,"losses":8,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":23,"wins":23},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":24},"gpt-6-astra":{"draws":5,"losses":42,"wins":1},"gpt-6-luna":{"draws":2,"losses":2,"wins":6},"gpt-6-sol":{"draws":3,"losses":10,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":7,"wins":15},"inclusionai/ling-3.0-flash":{"draws":0,"losses":3,"wins":9},"meituan/longcat-2.0":{"draws":6,"losses":8,"wins":18},"meta/muse-glimmer-30b":{"draws":8,"losses":2,"wins":22},"meta/muse-spark-1.2":{"draws":2,"losses":16,"wins":26},"meta/muse-spark-1.3":{"draws":8,"losses":12,"wins":22},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":4,"losses":5,"wins":11},"moonshotai/kimi-k3":{"draws":12,"losses":9,"wins":21},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":3},"o3":{"draws":10,"losses":22,"wins":18},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":21},"poolside/laguna-s-2.1":{"draws":13,"losses":1,"wins":22},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":18,"wins":23},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":13},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":11},"qwen/qwen3.8-max":{"draws":11,"losses":20,"wins":19},"qwen/qwen3.8-max-0902":{"draws":0,"losses":3,"wins":5},"stealth/ox-alpha":{"draws":36,"losses":48,"wins":74},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":10,"losses":6,"wins":24},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":15},"thinkingmachines/inkling-small":{"draws":16,"losses":8,"wins":22},"x-ai/grok-4.5":{"draws":7,"losses":8,"wins":17},"x-ai/grok-4.6":{"draws":5,"losses":21,"wins":22},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":4,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":15,"losses":15,"wins":30},"z-ai/glm-5.3":{"draws":7,"losses":23,"wins":14},"z-ai/glm-5.3-flash":{"draws":13,"losses":13,"wins":8},"z-ai/glm-5.3-flashx":{"draws":1,"losses":2,"wins":5}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":6},"claude-fable-5":{"draws":1,"losses":2,"wins":5},"claude-fable-5-1":{"draws":3,"losses":5,"wins":0},"claude-opus-4-5":{"draws":0,"losses":0,"wins":6},"claude-opus-4-8":{"draws":0,"losses":3,"wins":3},"claude-opus-5":{"draws":2,"losses":7,"wins":3},"claude-opus-5-5":{"draws":7,"losses":38,"wins":7},"claude-sonnet-5":{"draws":3,"losses":2,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":3,"losses":1,"wins":2},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":1,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":0,"wins":10},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":5,"losses":1,"wins":6},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":14},"google/gemini-3.6-flash":{"draws":6,"losses":4,"wins":10},"google/gemini-3.8-flash":{"draws":0,"losses":1,"wins":5},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":5,"losses":0,"wins":1},"gpt-5.4":{"draws":0,"losses":2,"wins":4},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":3,"wins":9},"gpt-5.5":{"draws":5,"losses":0,"wins":3},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":0,"wins":4},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":4},"gpt-6-astra":{"draws":1,"losses":8,"wins":1},"gpt-6-luna":{"draws":10,"losses":8,"wins":28},"gpt-6-sol":{"draws":7,"losses":24,"wins":17},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":5},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":7},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":6},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":7},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":4},"o3":{"draws":0,"losses":3,"wins":15},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":3},"poolside/laguna-s-2.1":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":1},"qwen/qwen3.8-flash":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.8-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.8-max-0902":{"draws":4,"losses":8,"wins":14},"stealth/ox-alpha":{"draws":4,"losses":6,"wins":18},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":1,"losses":2,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":2,"wins":5},"thinkingmachines/inkling-small":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":4},"x-ai/grok-4.6":{"draws":3,"losses":4,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":14,"wins":10},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":5,"wins":18},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":8,"wins":10},"z-ai/glm-5.2":{"draws":3,"losses":2,"wins":7},"z-ai/glm-5.3":{"draws":2,"losses":6,"wins":2},"z-ai/glm-5.3-flash":{"draws":3,"losses":3,"wins":4},"z-ai/glm-5.3-flashx":{"draws":8,"losses":3,"wins":15}}},"medium":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":7,"wins":17},"claude-fable-5":{"draws":6,"losses":17,"wins":9},"claude-fable-5-1":{"draws":1,"losses":28,"wins":3},"claude-opus-4-5":{"draws":11,"losses":15,"wins":20},"claude-opus-4-8":{"draws":4,"losses":3,"wins":7},"claude-opus-5":{"draws":5,"losses":13,"wins":4},"claude-opus-5-5":{"draws":0,"losses":4,"wins":2},"claude-sonnet-5":{"draws":17,"losses":20,"wins":11},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":11,"losses":19,"wins":10},"deepseek/deepseek-v4-pro":{"draws":15,"losses":16,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":13,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":1,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":3,"wins":10},"google/gemini-3.5-flash":{"draws":10,"losses":12,"wins":12},"google/gemini-3.5-flash-lite":{"draws":23,"losses":20,"wins":37},"google/gemini-3.6-flash":{"draws":18,"losses":28,"wins":22},"google/gemini-3.8-flash":{"draws":8,"losses":15,"wins":9},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":3,"wins":5},"gpt-5.4":{"draws":7,"losses":3,"wins":8},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":3},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":4},"gpt-5.5":{"draws":6,"losses":1,"wins":3},"gpt-5.6-luna":{"draws":12,"losses":9,"wins":21},"gpt-5.6-sol":{"draws":8,"losses":21,"wins":7},"gpt-5.6-terra":{"draws":13,"losses":15,"wins":10},"gpt-6-astra":{"draws":4,"losses":16,"wins":8},"gpt-6-luna":{"draws":0,"losses":1,"wins":3},"gpt-6-sol":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":15,"losses":12,"wins":7},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":5},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":11},"meta/muse-glimmer-30b":{"draws":14,"losses":11,"wins":17},"meta/muse-spark-1.2":{"draws":6,"losses":7,"wins":11},"meta/muse-spark-1.3":{"draws":7,"losses":10,"wins":9},"minimax/minimax-m3":{"draws":0,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":7,"losses":7,"wins":8},"moonshotai/kimi-k3":{"draws":7,"losses":15,"wins":8},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":6,"wins":7},"o3":{"draws":5,"losses":15,"wins":14},"openai/gpt-oss-120b":{"draws":8,"losses":11,"wins":13},"poolside/laguna-s-2.1":{"draws":13,"losses":9,"wins":10},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":12,"wins":10},"qwen/qwen3.8-27b":{"draws":3,"losses":10,"wins":9},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"wins":11},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":18},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":29,"losses":47,"wins":36},"stepfun/step-3.7-flash":{"draws":2,"losses":3,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":13,"losses":22,"wins":9},"thinkingmachines/inkling":{"draws":8,"losses":9,"wins":21},"thinkingmachines/inkling-small":{"draws":17,"losses":7,"wins":20},"x-ai/grok-4.5":{"draws":9,"losses":14,"wins":3},"x-ai/grok-4.6":{"draws":15,"losses":10,"wins":7},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":8,"losses":4,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":13,"losses":19,"wins":16},"z-ai/glm-5.3":{"draws":8,"losses":19,"wins":7},"z-ai/glm-5.3-flash":{"draws":10,"losses":17,"wins":7},"z-ai/glm-5.3-flashx":{"draws":1,"losses":6,"wins":1}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":6,"wins":15},"claude-fable-5":{"draws":6,"losses":9,"wins":15},"claude-fable-5-1":{"draws":0,"losses":46,"wins":10},"claude-opus-4-5":{"draws":10,"losses":3,"wins":27},"claude-opus-4-8":{"draws":4,"losses":0,"wins":4},"claude-opus-5":{"draws":2,"losses":35,"wins":9},"claude-opus-5-5":{"draws":2,"losses":7,"wins":1},"claude-sonnet-5":{"draws":10,"losses":9,"wins":27},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":12,"losses":3,"wins":29},"deepseek/deepseek-v4-pro":{"draws":8,"losses":11,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":9,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":3},"google/gemini-3.5-flash":{"draws":9,"losses":13,"wins":28},"google/gemini-3.5-flash-lite":{"draws":14,"losses":14,"wins":32},"google/gemini-3.6-flash":{"draws":8,"losses":31,"wins":33},"google/gemini-3.8-flash":{"draws":5,"losses":11,"wins":28},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":4,"losses":5,"wins":7},"gpt-5.4":{"draws":11,"losses":12,"wins":29},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":5},"gpt-5.4-nano":{"draws":1,"losses":3,"wins":6},"gpt-5.5":{"draws":1,"losses":3,"wins":8},"gpt-5.6-luna":{"draws":7,"losses":7,"wins":14},"gpt-5.6-sol":{"draws":4,"losses":23,"wins":23},"gpt-5.6-terra":{"draws":15,"losses":7,"wins":30},"gpt-6-astra":{"draws":5,"losses":37,"wins":10},"gpt-6-luna":{"draws":3,"losses":0,"wins":5},"gpt-6-sol":{"draws":4,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":3,"wins":13},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":2,"losses":4,"wins":16},"meta/muse-glimmer-30b":{"draws":6,"losses":5,"wins":7},"meta/muse-spark-1.2":{"draws":5,"losses":11,"wins":14},"meta/muse-spark-1.3":{"draws":6,"losses":15,"wins":25},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":9,"wins":31},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":8},"o3":{"draws":3,"losses":4,"wins":35},"openai/gpt-oss-120b":{"draws":12,"losses":5,"wins":17},"poolside/laguna-s-2.1":{"draws":4,"losses":8,"wins":10},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":11,"wins":24},"qwen/qwen3.8-27b":{"draws":7,"losses":4,"wins":11},"qwen/qwen3.8-flash":{"draws":9,"losses":3,"wins":16},"qwen/qwen3.8-max":{"draws":4,"losses":16,"wins":22},"qwen/qwen3.8-max-0902":{"draws":3,"losses":3,"wins":6},"stealth/ox-alpha":{"draws":41,"losses":32,"wins":85},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":10},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":8},"tencent/hy4-preview":{"draws":7,"losses":6,"wins":31},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":12},"thinkingmachines/inkling-small":{"draws":10,"losses":7,"wins":19},"x-ai/grok-4.5":{"draws":8,"losses":12,"wins":14},"x-ai/grok-4.6":{"draws":13,"losses":21,"wins":16},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":16,"losses":10,"wins":32},"z-ai/glm-5.3":{"draws":6,"losses":25,"wins":15},"z-ai/glm-5.3-flash":{"draws":12,"losses":13,"wins":27},"z-ai/glm-5.3-flashx":{"draws":0,"losses":3,"wins":7}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":0,"wins":19},"claude-fable-5":{"draws":3,"losses":10,"wins":41},"claude-fable-5-1":{"draws":3,"losses":30,"wins":17},"claude-opus-4-5":{"draws":2,"losses":1,"wins":53},"claude-opus-4-8":{"draws":2,"losses":3,"wins":9},"claude-opus-5":{"draws":4,"losses":9,"wins":13},"claude-opus-5-5":{"draws":1,"losses":5,"wins":4},"claude-sonnet-5":{"draws":5,"losses":2,"wins":45},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":5,"losses":1,"wins":32},"deepseek/deepseek-v4-pro":{"draws":3,"losses":1,"wins":36},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":0,"wins":8},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":41},"google/gemini-3.5-flash-lite":{"draws":8,"losses":0,"wins":44},"google/gemini-3.6-flash":{"draws":3,"losses":14,"wins":53},"google/gemini-3.8-flash":{"draws":6,"losses":4,"wins":40},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":14},"gpt-5.4":{"draws":7,"losses":8,"wins":35},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":8},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":6},"gpt-5.5":{"draws":2,"losses":4,"wins":12},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":15},"gpt-5.6-sol":{"draws":6,"losses":11,"wins":43},"gpt-5.6-terra":{"draws":5,"losses":3,"wins":28},"gpt-6-astra":{"draws":4,"losses":41,"wins":9},"gpt-6-luna":{"draws":0,"losses":0,"wins":6},"gpt-6-sol":{"draws":0,"losses":6,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":14},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":18},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":17},"meta/muse-spark-1.2":{"draws":6,"losses":6,"wins":26},"meta/muse-spark-1.3":{"draws":2,"losses":2,"wins":32},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":3,"wins":34},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":12},"o3":{"draws":0,"losses":3,"wins":37},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":19},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":20},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":6,"wins":44},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-flash":{"draws":1,"losses":2,"wins":29},"qwen/qwen3.8-max":{"draws":1,"losses":2,"wins":39},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":4},"stealth/ox-alpha":{"draws":13,"losses":12,"wins":139},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":9},"tencent/hy4-preview":{"draws":2,"losses":7,"wins":31},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":19},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":33},"x-ai/grok-4.5":{"draws":0,"losses":5,"wins":27},"x-ai/grok-4.6":{"draws":2,"losses":10,"wins":40},"x-ai/grok-4.7":{"draws":1,"losses":0,"wins":11},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":2},"z-ai/glm-5.2":{"draws":9,"losses":1,"wins":36},"z-ai/glm-5.3":{"draws":4,"losses":10,"wins":40},"z-ai/glm-5.3-flash":{"draws":3,"losses":7,"wins":44},"z-ai/glm-5.3-flashx":{"draws":0,"losses":1,"wins":7}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":10,"wins":22},"claude-fable-5":{"draws":7,"losses":36,"wins":3},"claude-fable-5-1":{"draws":3,"losses":59,"wins":0},"claude-opus-4-5":{"draws":15,"losses":13,"wins":26},"claude-opus-4-8":{"draws":11,"losses":12,"wins":7},"claude-opus-5":{"draws":12,"losses":40,"wins":14},"claude-opus-5-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":24,"losses":20,"wins":52},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":12},"deepseek/deepseek-v4-flash":{"draws":14,"losses":14,"wins":34},"deepseek/deepseek-v4-pro":{"draws":5,"losses":17,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":17,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":15},"google/gemini-3.5-flash":{"draws":12,"losses":23,"wins":17},"google/gemini-3.5-flash-lite":{"draws":49,"losses":41,"wins":108},"google/gemini-3.6-flash":{"draws":40,"losses":81,"wins":67},"google/gemini-3.8-flash":{"draws":12,"losses":29,"wins":17},"google/gemma-4-31b-it":{"draws":6,"losses":9,"wins":5},"gpt-4.1":{"draws":3,"losses":0,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":5,"losses":9,"wins":10},"gpt-5.4":{"draws":19,"losses":51,"wins":20},"gpt-5.4-mini":{"draws":9,"losses":6,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":13,"wins":23},"gpt-5.5":{"draws":13,"losses":12,"wins":5},"gpt-5.6-luna":{"draws":28,"losses":27,"wins":35},"gpt-5.6-sol":{"draws":16,"losses":66,"wins":16},"gpt-5.6-terra":{"draws":10,"losses":9,"wins":17},"gpt-6-astra":{"draws":6,"losses":35,"wins":3},"gpt-6-luna":{"draws":6,"losses":1,"wins":5},"gpt-6-sol":{"draws":3,"losses":9,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":5,"wins":23},"inclusionai/ling-3.0-flash":{"draws":6,"losses":3,"wins":23},"meituan/longcat-2.0":{"draws":15,"losses":10,"wins":42},"meta/muse-glimmer-30b":{"draws":6,"losses":7,"wins":21},"meta/muse-spark-1.2":{"draws":21,"losses":29,"wins":20},"meta/muse-spark-1.3":{"draws":9,"losses":26,"wins":13},"minimax/minimax-m3":{"draws":6,"losses":2,"wins":12},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":6},"moonshotai/kimi-k3":{"draws":40,"losses":33,"wins":29},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":7,"wins":6},"o3":{"draws":14,"losses":44,"wins":92},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":24},"poolside/laguna-s-2.1":{"draws":20,"losses":3,"wins":35},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":20,"wins":22},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":11},"qwen/qwen3.8-flash":{"draws":10,"losses":9,"wins":13},"qwen/qwen3.8-max":{"draws":7,"losses":25,"wins":13},"qwen/qwen3.8-max-0902":{"draws":4,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":41,"losses":59,"wins":51},"stepfun/step-3.7-flash":{"draws":6,"losses":12,"wins":16},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":5},"tencent/hy4-preview":{"draws":9,"losses":19,"wins":12},"thinkingmachines/inkling":{"draws":18,"losses":12,"wins":40},"thinkingmachines/inkling-small":{"draws":6,"losses":3,"wins":34},"x-ai/grok-4.5":{"draws":31,"losses":41,"wins":30},"x-ai/grok-4.6":{"draws":14,"losses":30,"wins":8},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":3},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":12},"xiaomi/mimo-v2.5":{"draws":19,"losses":11,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":22,"losses":9,"wins":19},"z-ai/glm-5.3":{"draws":15,"losses":25,"wins":10},"z-ai/glm-5.3-flash":{"draws":12,"losses":20,"wins":18},"z-ai/glm-5.3-flashx":{"draws":0,"losses":2,"wins":0}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":2,"wins":2},"claude-fable-5":{"draws":6,"losses":8,"wins":4},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":23,"losses":20,"wins":29},"claude-opus-4-8":{"draws":10,"losses":24,"wins":8},"claude-opus-5":{"draws":9,"losses":54,"wins":1},"claude-opus-5-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":4,"losses":4,"wins":4},"cohere/north-mini-code":{"draws":14,"losses":4,"wins":24},"deepseek/deepseek-v4-flash":{"draws":21,"losses":3,"wins":10},"deepseek/deepseek-v4-pro":{"draws":6,"losses":6,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":9,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":16,"losses":2,"wins":24},"google/gemini-3.5-flash":{"draws":13,"losses":5,"wins":6},"google/gemini-3.5-flash-lite":{"draws":19,"losses":3,"wins":12},"google/gemini-3.6-flash":{"draws":16,"losses":19,"wins":15},"google/gemini-3.8-flash":{"draws":3,"losses":6,"wins":5},"google/gemma-4-31b-it":{"draws":13,"losses":0,"wins":17},"gpt-4.1":{"draws":12,"losses":4,"wins":6},"gpt-5":{"draws":14,"losses":11,"wins":17},"gpt-5.4":{"draws":2,"losses":2,"wins":6},"gpt-5.4-mini":{"draws":17,"losses":15,"wins":8},"gpt-5.4-nano":{"draws":17,"losses":17,"wins":26},"gpt-5.5":{"draws":18,"losses":13,"wins":9},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":11,"losses":7,"wins":4},"gpt-5.6-terra":{"draws":6,"losses":1,"wins":9},"gpt-6-astra":{"draws":0,"losses":24,"wins":0},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":18,"losses":0,"wins":8},"meituan/longcat-2.0":{"draws":10,"losses":13,"wins":13},"meta/muse-glimmer-30b":{"draws":6,"losses":3,"wins":5},"meta/muse-spark-1.2":{"draws":4,"losses":3,"wins":11},"meta/muse-spark-1.3":{"draws":7,"losses":6,"wins":7},"minimax/minimax-m3":{"draws":14,"losses":8,"wins":8},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":8,"wins":4},"moonshotai/kimi-k3":{"draws":6,"losses":11,"wins":7},"nex-agi/nex-n2-pro":{"draws":21,"losses":0,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":6,"wins":10},"o3":{"draws":10,"losses":4,"wins":16},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":19,"losses":6,"wins":21},"qwen/qwen3.7-max":{"draws":19,"losses":4,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":7,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":2,"wins":4},"qwen/qwen3.8-flash":{"draws":6,"losses":3,"wins":1},"qwen/qwen3.8-max":{"draws":9,"losses":4,"wins":5},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":1},"stealth/ox-alpha":{"draws":19,"losses":29,"wins":8},"stepfun/step-3.7-flash":{"draws":9,"losses":6,"wins":3},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":8,"losses":9,"wins":5},"thinkingmachines/inkling":{"draws":15,"losses":9,"wins":14},"thinkingmachines/inkling-small":{"draws":8,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":12,"losses":13,"wins":11},"x-ai/grok-4.6":{"draws":6,"losses":8,"wins":6},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":18},"xiaomi/mimo-v2.5":{"draws":36,"losses":6,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":6,"wins":17},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":32,"losses":18,"wins":32},"z-ai/glm-5.3":{"draws":1,"losses":2,"wins":3},"z-ai/glm-5.3-flash":{"draws":5,"losses":11,"wins":8}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":12},"claude-fable-5":{"draws":3,"losses":9,"wins":26},"claude-fable-5-1":{"draws":1,"losses":16,"wins":5},"claude-opus-4-5":{"draws":21,"losses":14,"wins":115},"claude-opus-4-8":{"draws":16,"losses":18,"wins":46},"claude-opus-5":{"draws":27,"losses":111,"wins":84},"claude-opus-5-5":{"draws":1,"losses":11,"wins":6},"claude-sonnet-5":{"draws":2,"losses":4,"wins":24},"cohere/north-mini-code":{"draws":1,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":9,"losses":2,"wins":37},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":2,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":6,"wins":3},"google/gemini-3.1-flash-lite":{"draws":11,"losses":0,"wins":21},"google/gemini-3.5-flash":{"draws":6,"losses":5,"wins":35},"google/gemini-3.5-flash-lite":{"draws":15,"losses":9,"wins":66},"google/gemini-3.6-flash":{"draws":7,"losses":15,"wins":62},"google/gemini-3.8-flash":{"draws":7,"losses":6,"wins":27},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":15},"gpt-4.1":{"draws":2,"losses":4,"wins":24},"gpt-5":{"draws":8,"losses":4,"wins":58},"gpt-5.4":{"draws":1,"losses":3,"wins":16},"gpt-5.4-mini":{"draws":8,"losses":5,"wins":41},"gpt-5.4-nano":{"draws":10,"losses":11,"wins":51},"gpt-5.5":{"draws":9,"losses":34,"wins":55},"gpt-5.6-luna":{"draws":2,"losses":7,"wins":17},"gpt-5.6-sol":{"draws":4,"losses":5,"wins":27},"gpt-5.6-terra":{"draws":3,"losses":2,"wins":11},"gpt-6-astra":{"draws":2,"losses":21,"wins":1},"gpt-6-luna":{"draws":0,"losses":1,"wins":13},"gpt-6-sol":{"draws":2,"losses":6,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":5,"losses":3,"wins":20},"meituan/longcat-2.0":{"draws":6,"losses":9,"wins":65},"meta/muse-glimmer-30b":{"draws":1,"losses":3,"wins":14},"meta/muse-spark-1.2":{"draws":1,"losses":6,"wins":13},"meta/muse-spark-1.3":{"draws":3,"losses":4,"wins":31},"minimax/minimax-m3":{"draws":3,"losses":9,"wins":30},"mistralai/mistral-medium-3-5":{"draws":1,"losses":1,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":0,"wins":25},"moonshotai/kimi-k3":{"draws":8,"losses":3,"wins":41},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":0,"wins":47},"o3":{"draws":0,"losses":1,"wins":55},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":25},"poolside/laguna-s-2.1":{"draws":5,"losses":6,"wins":71},"qwen/qwen3.7-max":{"draws":9,"losses":7,"wins":48},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":1,"wins":14},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":6},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":20},"qwen/qwen3.8-max":{"draws":1,"losses":0,"wins":15},"qwen/qwen3.8-max-0902":{"draws":4,"losses":4,"wins":8},"stealth/ox-alpha":{"draws":11,"losses":8,"wins":72},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":24},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":33},"tencent/hy4-preview":{"draws":1,"losses":3,"wins":18},"thinkingmachines/inkling":{"draws":12,"losses":6,"wins":46},"thinkingmachines/inkling-small":{"draws":4,"losses":1,"wins":17},"x-ai/grok-4.5":{"draws":8,"losses":14,"wins":40},"x-ai/grok-4.6":{"draws":5,"losses":7,"wins":13},"x-ai/grok-4.7":{"draws":2,"losses":6,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":13},"xiaomi/mimo-v2.5":{"draws":23,"losses":7,"wins":76},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":0,"wins":27},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":16,"losses":9,"wins":69},"z-ai/glm-5.3":{"draws":4,"losses":9,"wins":15},"z-ai/glm-5.3-flash":{"draws":3,"losses":9,"wins":32},"z-ai/glm-5.3-flashx":{"draws":0,"losses":0,"wins":10}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":4},"claude-fable-5":{"draws":0,"losses":0,"wins":4},"claude-fable-5-1":{"draws":1,"losses":5,"wins":8},"claude-opus-4-5":{"draws":0,"losses":0,"wins":14},"claude-opus-4-8":{"draws":0,"losses":0,"wins":10},"claude-opus-5":{"draws":1,"losses":4,"wins":7},"claude-opus-5-5":{"draws":4,"losses":18,"wins":22},"claude-sonnet-5":{"draws":0,"losses":0,"wins":8},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":0,"wins":14},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":10},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":0,"losses":0,"wins":22},"google/gemini-3.8-flash":{"draws":1,"losses":0,"wins":5},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":8},"gpt-5.4":{"draws":0,"losses":1,"wins":7},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":10},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":8},"gpt-5.5":{"draws":0,"losses":0,"wins":8},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":3},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":12},"gpt-6-astra":{"draws":0,"losses":3,"wins":3},"gpt-6-luna":{"draws":2,"losses":0,"wins":50},"gpt-6-sol":{"draws":3,"losses":12,"wins":39},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":8},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":7},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":10},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":4},"meta/muse-spark-1.3":{"draws":0,"losses":0,"wins":6},"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":2},"moonshotai/kimi-k3":{"draws":1,"losses":0,"wins":7},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":4},"o3":{"draws":0,"losses":0,"wins":6},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":12},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":10},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":0,"losses":0,"wins":10},"qwen/qwen3.8-max-0902":{"draws":1,"losses":0,"wins":11},"stealth/ox-alpha":{"draws":1,"losses":3,"wins":32},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":7},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":11},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":10},"x-ai/grok-4.6":{"draws":0,"losses":0,"wins":16},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":25},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":0,"wins":25},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":18},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":20},"z-ai/glm-5.3":{"draws":0,"losses":0,"wins":14},"z-ai/glm-5.3-flash":{"draws":2,"losses":1,"wins":11},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":34}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":5,"wins":35},"claude-fable-5":{"draws":12,"losses":31,"wins":9},"claude-fable-5-1":{"draws":5,"losses":62,"wins":1},"claude-opus-4-5":{"draws":20,"losses":41,"wins":15},"claude-opus-4-8":{"draws":3,"losses":3,"wins":0},"claude-opus-5":{"draws":4,"losses":12,"wins":6},"claude-opus-5-5":{"draws":1,"losses":2,"wins":1},"claude-sonnet-5":{"draws":19,"losses":29,"wins":16},"deepseek/deepseek-v4-flash":{"draws":24,"losses":10,"wins":28},"deepseek/deepseek-v4-pro":{"draws":18,"losses":15,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":19,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":2,"wins":3},"google/gemini-3.1-flash-lite":{"draws":10,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":22,"losses":19,"wins":13},"google/gemini-3.5-flash-lite":{"draws":60,"losses":44,"wins":78},"google/gemini-3.6-flash":{"draws":50,"losses":68,"wins":34},"google/gemini-3.8-flash":{"draws":13,"losses":24,"wins":9},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":2},"gpt-4.1":{"draws":2,"losses":1,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":7,"losses":3,"wins":4},"gpt-5.4":{"draws":29,"losses":55,"wins":14},"gpt-5.4-mini":{"draws":6,"losses":1,"wins":3},"gpt-5.4-nano":{"draws":2,"losses":6,"wins":4},"gpt-5.5":{"draws":7,"losses":10,"wins":1},"gpt-5.6-luna":{"draws":32,"losses":24,"wins":46},"gpt-5.6-sol":{"draws":14,"losses":82,"wins":15},"gpt-5.6-terra":{"draws":17,"losses":16,"wins":7},"gpt-6-astra":{"draws":3,"losses":49,"wins":2},"gpt-6-luna":{"draws":1,"losses":6,"wins":5},"gpt-6-sol":{"draws":0,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":18,"losses":5,"wins":19},"inclusionai/ling-3.0-flash":{"draws":11,"losses":4,"wins":23},"meituan/longcat-2.0":{"draws":23,"losses":5,"wins":28},"meta/muse-glimmer-30b":{"draws":21,"losses":5,"wins":22},"meta/muse-spark-1.2":{"draws":21,"losses":32,"wins":19},"meta/muse-spark-1.3":{"draws":19,"losses":18,"wins":9},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":6},"mistralai/mistral-medium-3-5":{"draws":19,"losses":3,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":30,"losses":39,"wins":15},"nex-agi/nex-n2-pro":{"draws":5,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":2,"wins":10},"o3":{"draws":16,"losses":49,"wins":39},"openai/gpt-oss-120b":{"draws":20,"losses":7,"wins":29},"poolside/laguna-s-2.1":{"draws":24,"losses":5,"wins":25},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":13,"wins":9},"qwen/qwen3.8-27b":{"draws":6,"losses":10,"wins":10},"qwen/qwen3.8-flash":{"draws":15,"losses":12,"wins":13},"qwen/qwen3.8-max":{"draws":16,"losses":23,"wins":14},"qwen/qwen3.8-max-0902":{"draws":7,"losses":5,"wins":2},"stealth/ox-alpha":{"draws":41,"losses":86,"wins":41},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":10},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":23,"losses":21,"wins":6},"thinkingmachines/inkling":{"draws":24,"losses":8,"wins":42},"thinkingmachines/inkling-small":{"draws":15,"losses":8,"wins":25},"x-ai/grok-4.5":{"draws":16,"losses":38,"wins":16},"x-ai/grok-4.6":{"draws":16,"losses":24,"wins":10},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":1,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":2,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":28,"losses":17,"wins":25},"z-ai/glm-5.3":{"draws":5,"losses":39,"wins":2},"z-ai/glm-5.3-flash":{"draws":14,"losses":26,"wins":8},"z-ai/glm-5.3-flashx":{"draws":4,"losses":2,"wins":2}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":4,"wins":7},"claude-fable-5":{"draws":0,"losses":12,"wins":0},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":6,"losses":27,"wins":7},"claude-opus-4-8":{"draws":10,"losses":20,"wins":4},"claude-opus-5":{"draws":2,"losses":17,"wins":1},"claude-opus-5-5":{"draws":1,"losses":9,"wins":0},"claude-sonnet-5":{"draws":1,"losses":3,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":11,"losses":7,"wins":14},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":5,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":7,"wins":2},"google/gemini-3.1-flash-lite":{"draws":11,"losses":14,"wins":13},"google/gemini-3.5-flash":{"draws":6,"losses":10,"wins":4},"google/gemini-3.5-flash-lite":{"draws":18,"losses":8,"wins":12},"google/gemini-3.6-flash":{"draws":16,"losses":24,"wins":4},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":8,"wins":8},"gpt-4.1":{"draws":5,"losses":9,"wins":2},"gpt-5":{"draws":10,"losses":22,"wins":6},"gpt-5.4":{"draws":3,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":9,"losses":12,"wins":3},"gpt-5.4-nano":{"draws":13,"losses":22,"wins":9},"gpt-5.5":{"draws":14,"losses":14,"wins":6},"gpt-5.6-luna":{"draws":3,"losses":9,"wins":2},"gpt-5.6-sol":{"draws":3,"losses":9,"wins":2},"gpt-5.6-terra":{"draws":2,"losses":12,"wins":4},"gpt-6-astra":{"draws":0,"losses":10,"wins":0},"gpt-6-luna":{"draws":1,"losses":3,"wins":0},"gpt-6-sol":{"draws":2,"losses":5,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":6,"wins":6},"inclusionai/ling-3.0-flash":{"draws":10,"losses":15,"wins":9},"meituan/longcat-2.0":{"draws":13,"losses":19,"wins":6},"meta/muse-glimmer-30b":{"draws":0,"losses":6,"wins":2},"meta/muse-spark-1.2":{"draws":0,"losses":11,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":8,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":12},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":11,"losses":14,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":14},"o3":{"draws":11,"losses":18,"wins":9},"openai/gpt-oss-120b":{"draws":6,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":16,"losses":2,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":6,"losses":13,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":12,"wins":0},"qwen/qwen3.8-27b":{"draws":7,"losses":10,"wins":3},"qwen/qwen3.8-flash":{"draws":4,"losses":4,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":10,"wins":0},"qwen/qwen3.8-max-0902":{"draws":0,"losses":5,"wins":1},"stealth/ox-alpha":{"draws":7,"losses":24,"wins":7},"stepfun/step-3.7-flash":{"draws":8,"losses":7,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":7},"tencent/hy4-preview":{"draws":6,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":9,"losses":6,"wins":17},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":6,"losses":18,"wins":4},"x-ai/grok-4.6":{"draws":5,"losses":5,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":12,"wins":4},"xiaomi/mimo-v2.5":{"draws":22,"losses":14,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":11,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":5,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":7,"losses":21,"wins":10},"z-ai/glm-5.3":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":12,"wins":0},"z-ai/glm-5.3-flashx":{"draws":1,"losses":3,"wins":0}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":18,"wins":32},"claude-fable-5":{"draws":12,"losses":43,"wins":7},"claude-fable-5-1":{"draws":1,"losses":69,"wins":0},"claude-opus-4-5":{"draws":44,"losses":50,"wins":22},"claude-opus-4-8":{"draws":23,"losses":36,"wins":3},"claude-opus-5":{"draws":15,"losses":88,"wins":5},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":29,"losses":38,"wins":19},"cohere/north-mini-code":{"draws":18,"losses":16,"wins":20},"deepseek/deepseek-v4-flash":{"draws":31,"losses":37,"wins":38},"deepseek/deepseek-v4-pro":{"draws":20,"losses":34,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":28,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":26,"wins":2},"google/gemini-3.1-flash-lite":{"draws":18,"losses":35,"wins":59},"google/gemini-3.5-flash":{"draws":21,"losses":31,"wins":14},"google/gemini-3.5-flash-lite":{"draws":46,"losses":25,"wins":57},"google/gemini-3.6-flash":{"draws":45,"losses":73,"wins":30},"google/gemini-3.8-flash":{"draws":16,"losses":47,"wins":9},"google/gemma-4-31b-it":{"draws":9,"losses":19,"wins":30},"gpt-4.1":{"draws":22,"losses":15,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":32,"losses":24,"wins":6},"gpt-5.4":{"draws":21,"losses":40,"wins":5},"gpt-5.4-mini":{"draws":39,"losses":20,"wins":17},"gpt-5.4-nano":{"draws":30,"losses":25,"wins":39},"gpt-5.5":{"draws":39,"losses":25,"wins":4},"gpt-5.6-luna":{"draws":30,"losses":20,"wins":18},"gpt-5.6-sol":{"draws":9,"losses":55,"wins":6},"gpt-5.6-terra":{"draws":31,"losses":37,"wins":18},"gpt-6-astra":{"draws":1,"losses":55,"wins":2},"gpt-6-luna":{"draws":2,"losses":5,"wins":3},"gpt-6-sol":{"draws":2,"losses":18,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":23,"losses":6,"wins":23},"inclusionai/ling-3.0-flash":{"draws":38,"losses":24,"wins":30},"meituan/longcat-2.0":{"draws":32,"losses":24,"wins":28},"meta/muse-glimmer-30b":{"draws":27,"losses":10,"wins":33},"meta/muse-spark-1.2":{"draws":7,"losses":20,"wins":9},"meta/muse-spark-1.3":{"draws":18,"losses":40,"wins":12},"minimax/minimax-m3":{"draws":24,"losses":26,"wins":24},"mistralai/mistral-medium-3-5":{"draws":15,"losses":7,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":10,"wins":9},"moonshotai/kimi-k3":{"draws":28,"losses":37,"wins":19},"nex-agi/nex-n2-pro":{"draws":17,"losses":24,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":43,"losses":24,"wins":33},"o3":{"draws":15,"losses":44,"wins":39},"openai/gpt-oss-120b":{"draws":25,"losses":14,"wins":27},"poolside/laguna-s-2.1":{"draws":44,"losses":21,"wins":31},"qwen/qwen3.7-max":{"draws":23,"losses":17,"wins":16},"qwen/qwen3.7-plus":{"draws":23,"losses":24,"wins":21},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":39,"wins":12},"qwen/qwen3.8-27b":{"draws":10,"losses":18,"wins":20},"qwen/qwen3.8-flash":{"draws":17,"losses":15,"wins":10},"qwen/qwen3.8-max":{"draws":30,"losses":28,"wins":14},"qwen/qwen3.8-max-0902":{"draws":4,"losses":19,"wins":1},"stealth/ox-alpha":{"draws":73,"losses":98,"wins":42},"stepfun/step-3.7-flash":{"draws":20,"losses":26,"wins":14},"tencent/hy3-preview":{"draws":22,"losses":23,"wins":15},"tencent/hy4-preview":{"draws":17,"losses":28,"wins":9},"thinkingmachines/inkling":{"draws":27,"losses":36,"wins":35},"thinkingmachines/inkling-small":{"draws":39,"losses":7,"wins":36},"x-ai/grok-4.5":{"draws":14,"losses":56,"wins":10},"x-ai/grok-4.6":{"draws":29,"losses":47,"wins":6},"x-ai/grok-4.7":{"draws":0,"losses":14,"wins":0},"x-ai/grok-build-0.1":{"draws":18,"losses":9,"wins":13},"xiaomi/mimo-v2.5":{"draws":82,"losses":76,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":20,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":9,"wins":2},"z-ai/glm-5.2":{"draws":56,"losses":69,"wins":33},"z-ai/glm-5.3":{"draws":16,"losses":31,"wins":1},"z-ai/glm-5.3-flash":{"draws":16,"losses":34,"wins":14},"z-ai/glm-5.3-flashx":{"draws":6,"losses":8,"wins":0}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":11,"wins":32},"claude-fable-5":{"draws":9,"losses":24,"wins":19},"claude-fable-5-1":{"draws":5,"losses":51,"wins":2},"claude-opus-4-5":{"draws":10,"losses":12,"wins":24},"claude-opus-4-8":{"draws":4,"losses":6,"wins":6},"claude-opus-5":{"draws":1,"losses":16,"wins":1},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":19,"losses":12,"wins":25},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":14,"losses":15,"wins":29},"deepseek/deepseek-v4-pro":{"draws":7,"losses":12,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":14,"losses":22,"wins":14},"google/gemini-3.5-flash-lite":{"draws":18,"losses":23,"wins":49},"google/gemini-3.6-flash":{"draws":12,"losses":31,"wins":39},"google/gemini-3.8-flash":{"draws":7,"losses":29,"wins":14},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":7},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":0,"losses":2,"wins":4},"gpt-5.4":{"draws":8,"losses":29,"wins":15},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":7,"losses":3,"wins":10},"gpt-5.5":{"draws":2,"losses":9,"wins":3},"gpt-5.6-luna":{"draws":17,"losses":11,"wins":20},"gpt-5.6-sol":{"draws":4,"losses":28,"wins":16},"gpt-5.6-terra":{"draws":11,"losses":14,"wins":31},"gpt-6-astra":{"draws":0,"losses":31,"wins":9},"gpt-6-luna":{"draws":3,"losses":5,"wins":2},"gpt-6-sol":{"draws":0,"losses":4,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":15},"meituan/longcat-2.0":{"draws":9,"losses":1,"wins":16},"meta/muse-glimmer-30b":{"draws":10,"losses":6,"wins":16},"meta/muse-spark-1.2":{"draws":6,"losses":12,"wins":18},"meta/muse-spark-1.3":{"draws":1,"losses":20,"wins":21},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":3},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":23,"wins":11},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":8},"o3":{"draws":1,"losses":19,"wins":34},"openai/gpt-oss-120b":{"draws":13,"losses":7,"wins":20},"poolside/laguna-s-2.1":{"draws":10,"losses":8,"wins":22},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":5},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":23,"wins":14},"qwen/qwen3.8-27b":{"draws":1,"losses":8,"wins":13},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":13},"qwen/qwen3.8-max":{"draws":12,"losses":20,"wins":20},"qwen/qwen3.8-max-0902":{"draws":0,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":42,"losses":51,"wins":61},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":12,"losses":20,"wins":18},"thinkingmachines/inkling":{"draws":10,"losses":6,"wins":18},"thinkingmachines/inkling-small":{"draws":16,"losses":6,"wins":26},"x-ai/grok-4.5":{"draws":10,"losses":18,"wins":12},"x-ai/grok-4.6":{"draws":5,"losses":29,"wins":20},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":13,"losses":15,"wins":32},"z-ai/glm-5.3":{"draws":8,"losses":34,"wins":8},"z-ai/glm-5.3-flash":{"draws":6,"losses":21,"wins":17},"z-ai/glm-5.3-flashx":{"draws":2,"losses":3,"wins":5}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":17,"wins":19},"claude-fable-5":{"draws":7,"losses":28,"wins":7},"claude-fable-5-1":{"draws":1,"losses":48,"wins":3},"claude-opus-4-5":{"draws":12,"losses":12,"wins":16},"claude-opus-4-8":{"draws":4,"losses":4,"wins":10},"claude-opus-5":{"draws":3,"losses":14,"wins":3},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":15,"losses":10,"wins":21},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":16,"losses":19,"wins":19},"deepseek/deepseek-v4-pro":{"draws":12,"losses":22,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":9,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":6},"google/gemini-3.5-flash":{"draws":23,"losses":20,"wins":15},"google/gemini-3.5-flash-lite":{"draws":28,"losses":12,"wins":40},"google/gemini-3.6-flash":{"draws":24,"losses":44,"wins":20},"google/gemini-3.8-flash":{"draws":15,"losses":22,"wins":13},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-4.1":{"draws":1,"losses":0,"wins":7},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":6,"losses":2,"wins":2},"gpt-5.4":{"draws":10,"losses":19,"wins":11},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":7,"wins":8},"gpt-5.5":{"draws":7,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":14,"losses":21,"wins":11},"gpt-5.6-sol":{"draws":10,"losses":33,"wins":7},"gpt-5.6-terra":{"draws":12,"losses":21,"wins":19},"gpt-6-astra":{"draws":2,"losses":44,"wins":0},"gpt-6-luna":{"draws":2,"losses":2,"wins":4},"gpt-6-sol":{"draws":3,"losses":7,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":8,"wins":20},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":2},"meituan/longcat-2.0":{"draws":12,"losses":7,"wins":13},"meta/muse-glimmer-30b":{"draws":18,"losses":8,"wins":26},"meta/muse-spark-1.2":{"draws":16,"losses":14,"wins":16},"meta/muse-spark-1.3":{"draws":10,"losses":22,"wins":10},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":7},"mistralai/mistral-medium-3-5":{"draws":7,"losses":8,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":10,"losses":18,"wins":8},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":8},"o3":{"draws":6,"losses":20,"wins":24},"openai/gpt-oss-120b":{"draws":5,"losses":10,"wins":15},"poolside/laguna-s-2.1":{"draws":15,"losses":11,"wins":18},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":3,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":14,"wins":18},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":11},"qwen/qwen3.8-flash":{"draws":13,"losses":10,"wins":7},"qwen/qwen3.8-max":{"draws":23,"losses":15,"wins":10},"qwen/qwen3.8-max-0902":{"draws":2,"losses":1,"wins":3},"stealth/ox-alpha":{"draws":45,"losses":70,"wins":45},"stepfun/step-3.7-flash":{"draws":2,"losses":7,"wins":9},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":5},"tencent/hy4-preview":{"draws":13,"losses":19,"wins":10},"thinkingmachines/inkling":{"draws":14,"losses":9,"wins":19},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":30},"x-ai/grok-4.5":{"draws":12,"losses":22,"wins":20},"x-ai/grok-4.6":{"draws":15,"losses":27,"wins":16},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":2,"losses":6,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":5,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":1,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":7,"wins":0},"z-ai/glm-5.2":{"draws":28,"losses":16,"wins":32},"z-ai/glm-5.3":{"draws":15,"losses":23,"wins":8},"z-ai/glm-5.3-flash":{"draws":11,"losses":20,"wins":13},"z-ai/glm-5.3-flashx":{"draws":1,"losses":3,"wins":0}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":1,"wins":3},"claude-fable-5":{"draws":4,"losses":0,"wins":0},"claude-fable-5-1":{"draws":4,"losses":9,"wins":3},"claude-opus-4-5":{"draws":0,"losses":1,"wins":5},"claude-opus-4-8":{"draws":1,"losses":1,"wins":2},"claude-opus-5":{"draws":1,"losses":8,"wins":5},"claude-opus-5-5":{"draws":0,"losses":12,"wins":2},"claude-sonnet-5":{"draws":1,"losses":2,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-flash":{"draws":5,"losses":0,"wins":13},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":12,"wins":13},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash-lite":{"draws":4,"losses":3,"wins":13},"google/gemini-3.6-flash":{"draws":5,"losses":7,"wins":4},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":3,"losses":2,"wins":3},"gpt-5.4":{"draws":8,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":0,"wins":3},"gpt-5.5":{"draws":5,"losses":4,"wins":3},"gpt-5.6-luna":{"draws":8,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":4},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":4},"gpt-6-astra":{"draws":1,"losses":8,"wins":1},"gpt-6-luna":{"draws":5,"losses":2,"wins":5},"gpt-6-sol":{"draws":5,"losses":10,"wins":1},"inception/mercury-2.5-preview":{"draws":2,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":3,"losses":5,"wins":10},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":10},"meta/muse-spark-1.2":{"draws":4,"losses":3,"wins":3},"meta/muse-spark-1.3":{"draws":7,"losses":1,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":0,"wins":6},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":3,"wins":3},"o3":{"draws":1,"losses":0,"wins":11},"openai/gpt-oss-120b":{"draws":3,"losses":2,"wins":7},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":5,"wins":5},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":7,"losses":4,"wins":5},"qwen/qwen3.8-max-0902":{"draws":4,"losses":4,"wins":8},"stealth/ox-alpha":{"draws":11,"losses":17,"wins":14},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":4},"tencent/hy4-preview":{"draws":4,"losses":6,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":0,"wins":1},"thinkingmachines/inkling-small":{"draws":5,"losses":2,"wins":3},"x-ai/grok-4.5":{"draws":4,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":9,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":9,"losses":1,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":2,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":3,"wins":0},"z-ai/glm-5.2":{"draws":5,"losses":4,"wins":5},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":4},"z-ai/glm-5.3-flash":{"draws":2,"losses":3,"wins":7},"z-ai/glm-5.3-flashx":{"draws":7,"losses":6,"wins":5}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":7,"wins":2},"claude-fable-5":{"draws":1,"losses":4,"wins":1},"claude-fable-5-1":{"draws":0,"losses":12,"wins":0},"claude-opus-4-5":{"draws":15,"losses":39,"wins":2},"claude-opus-4-8":{"draws":12,"losses":29,"wins":3},"claude-opus-5":{"draws":7,"losses":22,"wins":3},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":4,"losses":11,"wins":1},"cohere/north-mini-code":{"draws":6,"losses":17,"wins":11},"deepseek/deepseek-v4-flash":{"draws":4,"losses":29,"wins":11},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":2,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":6,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":12,"wins":14},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":5},"google/gemini-3.5-flash-lite":{"draws":14,"losses":12,"wins":12},"google/gemini-3.6-flash":{"draws":5,"losses":16,"wins":3},"google/gemini-3.8-flash":{"draws":2,"losses":12,"wins":0},"google/gemma-4-31b-it":{"draws":9,"losses":14,"wins":11},"gpt-4.1":{"draws":5,"losses":5,"wins":2},"gpt-5":{"draws":12,"losses":14,"wins":2},"gpt-5.4":{"draws":2,"losses":12,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":19,"wins":6},"gpt-5.4-nano":{"draws":12,"losses":38,"wins":14},"gpt-5.5":{"draws":8,"losses":11,"wins":3},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":13,"wins":4},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"gpt-6-luna":{"draws":4,"losses":4,"wins":0},"gpt-6-sol":{"draws":2,"losses":10,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":8,"losses":5,"wins":11},"meituan/longcat-2.0":{"draws":5,"losses":17,"wins":14},"meta/muse-glimmer-30b":{"draws":8,"losses":5,"wins":3},"meta/muse-spark-1.2":{"draws":3,"losses":8,"wins":1},"meta/muse-spark-1.3":{"draws":0,"losses":8,"wins":0},"minimax/minimax-m3":{"draws":10,"losses":16,"wins":14},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":14,"wins":0},"moonshotai/kimi-k3":{"draws":3,"losses":8,"wins":1},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":20},"o3":{"draws":6,"losses":16,"wins":2},"openai/gpt-oss-120b":{"draws":2,"losses":10,"wins":2},"poolside/laguna-s-2.1":{"draws":6,"losses":14,"wins":10},"qwen/qwen3.7-max":{"draws":12,"losses":15,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":12,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":0},"qwen/qwen3.8-flash":{"draws":5,"losses":0,"wins":1},"qwen/qwen3.8-max":{"draws":4,"losses":4,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":8,"wins":0},"stealth/ox-alpha":{"draws":10,"losses":17,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":13,"wins":1},"tencent/hy3-preview":{"draws":5,"losses":0,"wins":7},"tencent/hy4-preview":{"draws":4,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":7,"losses":18,"wins":15},"thinkingmachines/inkling-small":{"draws":1,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":10,"losses":18,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":15,"wins":3},"xiaomi/mimo-v2.5":{"draws":25,"losses":28,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":20,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":3,"wins":0},"z-ai/glm-5.2":{"draws":17,"losses":31,"wins":8},"z-ai/glm-5.3":{"draws":3,"losses":5,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":7,"wins":2},"z-ai/glm-5.3-flashx":{"draws":0,"losses":14,"wins":0}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":5,"wins":20},"claude-fable-5":{"draws":13,"losses":30,"wins":11},"claude-fable-5-1":{"draws":6,"losses":52,"wins":0},"claude-opus-4-5":{"draws":11,"losses":15,"wins":22},"claude-opus-4-8":{"draws":1,"losses":6,"wins":5},"claude-opus-5":{"draws":4,"losses":31,"wins":3},"claude-opus-5-5":{"draws":1,"losses":6,"wins":1},"claude-sonnet-5":{"draws":15,"losses":7,"wins":30},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":13,"losses":6,"wins":15},"deepseek/deepseek-v4-pro":{"draws":13,"losses":8,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":11,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":6,"losses":12,"wins":10},"google/gemini-3.5-flash-lite":{"draws":21,"losses":14,"wins":37},"google/gemini-3.6-flash":{"draws":22,"losses":20,"wins":30},"google/gemini-3.8-flash":{"draws":16,"losses":22,"wins":18},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":1},"gpt-4.1":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":2,"wins":8},"gpt-5.4":{"draws":12,"losses":21,"wins":17},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":8},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":6},"gpt-5.5":{"draws":5,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":19,"losses":5,"wins":18},"gpt-5.6-sol":{"draws":8,"losses":33,"wins":15},"gpt-5.6-terra":{"draws":9,"losses":16,"wins":19},"gpt-6-astra":{"draws":6,"losses":44,"wins":2},"gpt-6-luna":{"draws":0,"losses":0,"wins":6},"gpt-6-sol":{"draws":2,"losses":4,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":16,"losses":1,"wins":17},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":8},"meituan/longcat-2.0":{"draws":5,"losses":10,"wins":15},"meta/muse-glimmer-30b":{"draws":11,"losses":6,"wins":15},"meta/muse-spark-1.2":{"draws":7,"losses":8,"wins":23},"meta/muse-spark-1.3":{"draws":9,"losses":18,"wins":15},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":21,"losses":9,"wins":22},"nex-agi/nex-n2-pro":{"draws":2,"losses":5,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":7},"o3":{"draws":7,"losses":9,"wins":24},"openai/gpt-oss-120b":{"draws":17,"losses":4,"wins":17},"poolside/laguna-s-2.1":{"draws":8,"losses":8,"wins":16},"qwen/qwen3.7-max":{"draws":3,"losses":2,"wins":1},"qwen/qwen3.7-plus":{"draws":5,"losses":0,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":13,"wins":19},"qwen/qwen3.8-27b":{"draws":9,"losses":10,"wins":9},"qwen/qwen3.8-flash":{"draws":13,"losses":7,"wins":14},"qwen/qwen3.8-max":{"draws":8,"losses":13,"wins":19},"qwen/qwen3.8-max-0902":{"draws":2,"losses":1,"wins":1},"stealth/ox-alpha":{"draws":40,"losses":45,"wins":68},"stepfun/step-3.7-flash":{"draws":3,"losses":1,"wins":10},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":5,"losses":22,"wins":19},"thinkingmachines/inkling":{"draws":11,"losses":7,"wins":10},"thinkingmachines/inkling-small":{"draws":10,"losses":8,"wins":14},"x-ai/grok-4.5":{"draws":8,"losses":13,"wins":17},"x-ai/grok-4.6":{"draws":12,"losses":20,"wins":10},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":16,"losses":22,"wins":30},"z-ai/glm-5.3":{"draws":10,"losses":22,"wins":16},"z-ai/glm-5.3-flash":{"draws":22,"losses":17,"wins":17},"z-ai/glm-5.3-flashx":{"draws":2,"losses":1,"wins":3}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":31,"wins":20},"claude-fable-5":{"draws":14,"losses":42,"wins":6},"claude-fable-5-1":{"draws":0,"losses":34,"wins":0},"claude-opus-4-5":{"draws":71,"losses":102,"wins":9},"claude-opus-4-8":{"draws":22,"losses":18,"wins":0},"claude-opus-5":{"draws":12,"losses":53,"wins":7},"claude-opus-5-5":{"draws":2,"losses":6,"wins":0},"claude-sonnet-5":{"draws":45,"losses":99,"wins":26},"cohere/north-mini-code":{"draws":18,"losses":10,"wins":2},"deepseek/deepseek-v4-flash":{"draws":41,"losses":46,"wins":21},"deepseek/deepseek-v4-pro":{"draws":27,"losses":35,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":27,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":13,"wins":2},"google/gemini-3.1-flash-lite":{"draws":16,"losses":11,"wins":17},"google/gemini-3.5-flash":{"draws":23,"losses":40,"wins":19},"google/gemini-3.5-flash-lite":{"draws":112,"losses":119,"wins":97},"google/gemini-3.6-flash":{"draws":131,"losses":158,"wins":42},"google/gemini-3.8-flash":{"draws":13,"losses":38,"wins":1},"google/gemma-4-31b-it":{"draws":6,"losses":12,"wins":4},"gpt-4.1":{"draws":9,"losses":5,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":7,"wins":7},"gpt-5":{"draws":17,"losses":10,"wins":13},"gpt-5.4":{"draws":50,"losses":89,"wins":11},"gpt-5.4-mini":{"draws":17,"losses":18,"wins":7},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":14},"gpt-5.5":{"draws":22,"losses":10,"wins":2},"gpt-5.6-luna":{"draws":63,"losses":83,"wins":30},"gpt-5.6-sol":{"draws":25,"losses":112,"wins":5},"gpt-5.6-terra":{"draws":21,"losses":41,"wins":6},"gpt-6-astra":{"draws":3,"losses":39,"wins":0},"gpt-6-luna":{"draws":6,"losses":11,"wins":1},"gpt-6-sol":{"draws":5,"losses":16,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":9,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":25,"losses":22,"wins":19},"inclusionai/ling-3.0-flash":{"draws":28,"losses":23,"wins":29},"meituan/longcat-2.0":{"draws":39,"losses":72,"wins":31},"meta/muse-glimmer-30b":{"draws":39,"losses":19,"wins":22},"meta/muse-spark-1.2":{"draws":23,"losses":70,"wins":13},"meta/muse-spark-1.3":{"draws":14,"losses":33,"wins":9},"minimax/minimax-m3":{"draws":12,"losses":8,"wins":12},"mistralai/mistral-medium-3-5":{"draws":23,"losses":16,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":66,"losses":88,"wins":20},"nex-agi/nex-n2-pro":{"draws":10,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":11,"wins":11},"o3":{"draws":51,"losses":171,"wins":38},"openai/gpt-oss-120b":{"draws":34,"losses":34,"wins":18},"poolside/laguna-s-2.1":{"draws":61,"losses":56,"wins":27},"qwen/qwen3.7-max":{"draws":10,"losses":6,"wins":6},"qwen/qwen3.7-plus":{"draws":14,"losses":7,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":37,"wins":5},"qwen/qwen3.8-27b":{"draws":9,"losses":31,"wins":10},"qwen/qwen3.8-flash":{"draws":22,"losses":25,"wins":3},"qwen/qwen3.8-max":{"draws":31,"losses":25,"wins":13},"qwen/qwen3.8-max-0902":{"draws":4,"losses":9,"wins":1},"stealth/ox-alpha":{"draws":82,"losses":139,"wins":28},"stepfun/step-3.7-flash":{"draws":20,"losses":29,"wins":15},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":20,"losses":36,"wins":10},"thinkingmachines/inkling":{"draws":53,"losses":40,"wins":53},"thinkingmachines/inkling-small":{"draws":41,"losses":28,"wins":36},"x-ai/grok-4.5":{"draws":44,"losses":90,"wins":10},"x-ai/grok-4.6":{"draws":33,"losses":35,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":17,"losses":10,"wins":5},"xiaomi/mimo-v2.5":{"draws":32,"losses":20,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":16,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":50,"losses":37,"wins":21},"z-ai/glm-5.3":{"draws":17,"losses":40,"wins":3},"z-ai/glm-5.3-flash":{"draws":23,"losses":30,"wins":13},"z-ai/glm-5.3-flashx":{"draws":0,"losses":12,"wins":0}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":11,"wins":26},"claude-fable-5":{"draws":12,"losses":37,"wins":23},"claude-fable-5-1":{"draws":2,"losses":61,"wins":9},"claude-opus-4-5":{"draws":32,"losses":40,"wins":78},"claude-opus-4-8":{"draws":18,"losses":20,"wins":32},"claude-opus-5":{"draws":8,"losses":54,"wins":22},"claude-opus-5-5":{"draws":1,"losses":9,"wins":2},"claude-sonnet-5":{"draws":33,"losses":35,"wins":52},"cohere/north-mini-code":{"draws":12,"losses":9,"wins":31},"deepseek/deepseek-v4-flash":{"draws":19,"losses":16,"wins":57},"deepseek/deepseek-v4-pro":{"draws":14,"losses":21,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":19,"wins":42},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":8,"wins":10},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":25},"google/gemini-3.5-flash":{"draws":17,"losses":26,"wins":27},"google/gemini-3.5-flash-lite":{"draws":73,"losses":41,"wins":157},"google/gemini-3.6-flash":{"draws":45,"losses":66,"wins":115},"google/gemini-3.8-flash":{"draws":11,"losses":28,"wins":27},"google/gemma-4-31b-it":{"draws":1,"losses":5,"wins":12},"gpt-4.1":{"draws":3,"losses":2,"wins":13},"gpt-4.1-nano":{"draws":8,"losses":0,"wins":0},"gpt-5":{"draws":10,"losses":7,"wins":19},"gpt-5.4":{"draws":34,"losses":56,"wins":44},"gpt-5.4-mini":{"draws":9,"losses":11,"wins":21},"gpt-5.4-nano":{"draws":14,"losses":9,"wins":31},"gpt-5.5":{"draws":19,"losses":13,"wins":20},"gpt-5.6-luna":{"draws":27,"losses":20,"wins":81},"gpt-5.6-sol":{"draws":21,"losses":62,"wins":49},"gpt-5.6-terra":{"draws":19,"losses":17,"wins":30},"gpt-6-astra":{"draws":9,"losses":64,"wins":5},"gpt-6-luna":{"draws":2,"losses":7,"wins":13},"gpt-6-sol":{"draws":3,"losses":12,"wins":11},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":14,"losses":4,"wins":26},"inclusionai/ling-3.0-flash":{"draws":29,"losses":4,"wins":35},"meituan/longcat-2.0":{"draws":37,"losses":14,"wins":61},"meta/muse-glimmer-30b":{"draws":18,"losses":10,"wins":26},"meta/muse-spark-1.2":{"draws":17,"losses":36,"wins":49},"meta/muse-spark-1.3":{"draws":10,"losses":27,"wins":25},"minimax/minimax-m3":{"draws":7,"losses":2,"wins":13},"mistralai/mistral-medium-3-5":{"draws":8,"losses":8,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":12},"moonshotai/kimi-k3":{"draws":38,"losses":46,"wins":76},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":16},"o3":{"draws":27,"losses":42,"wins":127},"openai/gpt-oss-120b":{"draws":15,"losses":8,"wins":21},"poolside/laguna-s-2.1":{"draws":31,"losses":17,"wins":52},"qwen/qwen3.7-max":{"draws":1,"losses":4,"wins":25},"qwen/qwen3.7-plus":{"draws":11,"losses":4,"wins":27},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":22,"wins":31},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":25},"qwen/qwen3.8-flash":{"draws":15,"losses":15,"wins":18},"qwen/qwen3.8-max":{"draws":18,"losses":20,"wins":32},"qwen/qwen3.8-max-0902":{"draws":7,"losses":4,"wins":9},"stealth/ox-alpha":{"draws":53,"losses":80,"wins":97},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":37},"tencent/hy3-preview":{"draws":10,"losses":5,"wins":5},"tencent/hy4-preview":{"draws":16,"losses":26,"wins":36},"thinkingmachines/inkling":{"draws":32,"losses":22,"wins":68},"thinkingmachines/inkling-small":{"draws":17,"losses":7,"wins":41},"x-ai/grok-4.5":{"draws":37,"losses":52,"wins":75},"x-ai/grok-4.6":{"draws":21,"losses":27,"wins":24},"x-ai/grok-4.7":{"draws":3,"losses":7,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":35,"losses":10,"wins":37},"xiaomi/mimo-v2.5-pro":{"draws":18,"losses":6,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":32,"losses":30,"wins":40},"z-ai/glm-5.3":{"draws":13,"losses":34,"wins":15},"z-ai/glm-5.3-flash":{"draws":6,"losses":30,"wins":22},"z-ai/glm-5.3-flashx":{"draws":4,"losses":8,"wins":6}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":4,"wins":17},"claude-fable-5":{"draws":12,"losses":16,"wins":20},"claude-fable-5-1":{"draws":3,"losses":51,"wins":6},"claude-opus-4-5":{"draws":21,"losses":11,"wins":18},"claude-opus-4-8":{"draws":3,"losses":3,"wins":8},"claude-opus-5":{"draws":7,"losses":17,"wins":8},"claude-opus-5-5":{"draws":1,"losses":7,"wins":2},"claude-sonnet-5":{"draws":17,"losses":14,"wins":19},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":17,"losses":7,"wins":28},"deepseek/deepseek-v4-pro":{"draws":20,"losses":10,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":9,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":13,"losses":13,"wins":20},"google/gemini-3.5-flash-lite":{"draws":22,"losses":3,"wins":37},"google/gemini-3.6-flash":{"draws":20,"losses":28,"wins":27},"google/gemini-3.8-flash":{"draws":10,"losses":14,"wins":14},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":5},"gpt-4.1":{"draws":3,"losses":1,"wins":4},"gpt-5":{"draws":6,"losses":7,"wins":5},"gpt-5.4":{"draws":15,"losses":20,"wins":21},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":2,"wins":4},"gpt-5.5":{"draws":4,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":13,"losses":12,"wins":27},"gpt-5.6-sol":{"draws":9,"losses":25,"wins":16},"gpt-5.6-terra":{"draws":17,"losses":9,"wins":18},"gpt-6-astra":{"draws":4,"losses":44,"wins":2},"gpt-6-luna":{"draws":0,"losses":1,"wins":3},"gpt-6-sol":{"draws":1,"losses":7,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":7},"inception/mercury-2.5-preview":{"draws":12,"losses":1,"wins":15},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":12},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":4},"meta/muse-glimmer-30b":{"draws":18,"losses":2,"wins":10},"meta/muse-spark-1.2":{"draws":7,"losses":17,"wins":8},"meta/muse-spark-1.3":{"draws":14,"losses":19,"wins":11},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":11,"losses":0,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":22,"losses":9,"wins":19},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":1,"wins":7},"o3":{"draws":9,"losses":16,"wins":29},"openai/gpt-oss-120b":{"draws":13,"losses":5,"wins":14},"poolside/laguna-s-2.1":{"draws":14,"losses":3,"wins":7},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":19,"wins":24},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"wins":19},"qwen/qwen3.8-flash":{"draws":15,"losses":6,"wins":17},"qwen/qwen3.8-max":{"draws":14,"losses":17,"wins":15},"qwen/qwen3.8-max-0902":{"draws":3,"losses":3,"wins":2},"stealth/ox-alpha":{"draws":43,"losses":48,"wins":81},"stepfun/step-3.7-flash":{"draws":5,"losses":0,"wins":7},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":2},"tencent/hy4-preview":{"draws":13,"losses":14,"wins":17},"thinkingmachines/inkling":{"draws":14,"losses":0,"wins":14},"thinkingmachines/inkling-small":{"draws":18,"losses":2,"wins":14},"x-ai/grok-4.5":{"draws":10,"losses":18,"wins":10},"x-ai/grok-4.6":{"draws":18,"losses":21,"wins":17},"x-ai/grok-4.7":{"draws":1,"losses":8,"wins":1},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":15,"losses":6,"wins":29},"z-ai/glm-5.3":{"draws":10,"losses":29,"wins":15},"z-ai/glm-5.3-flash":{"draws":13,"losses":17,"wins":22},"z-ai/glm-5.3-flashx":{"draws":0,"losses":2,"wins":2}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":1},"claude-fable-5":{"draws":0,"losses":9,"wins":1},"claude-fable-5-1":{"draws":2,"losses":4,"wins":0},"claude-opus-4-5":{"draws":8,"losses":15,"wins":23},"claude-opus-4-8":{"draws":12,"losses":12,"wins":4},"claude-opus-5":{"draws":5,"losses":27,"wins":2},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":3,"losses":4,"wins":1},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":3,"losses":6,"wins":9},"deepseek/deepseek-v4-pro":{"draws":1,"losses":3,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":10,"losses":8,"wins":10},"google/gemini-3.5-flash":{"draws":6,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":12,"wins":16},"google/gemini-3.6-flash":{"draws":1,"losses":9,"wins":4},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":4,"wins":6},"gpt-4.1":{"draws":2,"losses":3,"wins":1},"gpt-5":{"draws":1,"losses":10,"wins":3},"gpt-5.4":{"draws":1,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":2,"losses":13,"wins":11},"gpt-5.4-nano":{"draws":1,"losses":18,"wins":13},"gpt-5.5":{"draws":10,"losses":11,"wins":3},"gpt-5.6-luna":{"draws":0,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":6,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":0,"losses":1,"wins":1},"gpt-6-sol":{"draws":1,"losses":4,"wins":1},"inception/mercury-2.5-preview":{"draws":1,"losses":2,"wins":5},"inclusionai/ling-3.0-flash":{"draws":2,"losses":5,"wins":7},"meituan/longcat-2.0":{"draws":1,"losses":19,"wins":16},"meta/muse-glimmer-30b":{"draws":0,"losses":2,"wins":2},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":5,"wins":5},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":10},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":9,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":5,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":6,"wins":10},"o3":{"draws":4,"losses":20,"wins":4},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":8,"wins":12},"qwen/qwen3.7-max":{"draws":4,"losses":15,"wins":7},"qwen/qwen3.7-plus":{"draws":1,"losses":6,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":9,"wins":0},"qwen/qwen3.8-27b":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":6,"losses":5,"wins":5},"qwen/qwen3.8-max-0902":{"draws":0,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":6,"losses":18,"wins":2},"stepfun/step-3.7-flash":{"draws":2,"losses":16,"wins":0},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":2},"tencent/hy4-preview":{"draws":2,"losses":3,"wins":1},"thinkingmachines/inkling":{"draws":4,"losses":3,"wins":11},"thinkingmachines/inkling-small":{"draws":0,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":2,"losses":8,"wins":4},"x-ai/grok-4.6":{"draws":0,"losses":7,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":8,"wins":8},"xiaomi/mimo-v2.5":{"draws":9,"losses":7,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":14,"losses":13,"wins":3},"z-ai/glm-5.3":{"draws":0,"losses":7,"wins":1},"z-ai/glm-5.3-flash":{"draws":0,"losses":9,"wins":1}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":4,"wins":6},"claude-fable-5":{"draws":4,"losses":2,"wins":4},"claude-fable-5-1":{"draws":1,"losses":15,"wins":0},"claude-opus-4-5":{"draws":15,"losses":20,"wins":19},"claude-opus-4-8":{"draws":10,"losses":21,"wins":17},"claude-opus-5":{"draws":9,"losses":38,"wins":5},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":1,"losses":1,"wins":2},"cohere/north-mini-code":{"draws":8,"losses":4,"wins":20},"deepseek/deepseek-v4-flash":{"draws":11,"losses":5,"wins":8},"deepseek/deepseek-v4-pro":{"draws":7,"losses":3,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":11,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":10,"losses":0,"wins":16},"google/gemini-3.5-flash":{"draws":7,"losses":10,"wins":5},"google/gemini-3.5-flash-lite":{"draws":12,"losses":10,"wins":8},"google/gemini-3.6-flash":{"draws":2,"losses":20,"wins":14},"google/gemini-3.8-flash":{"draws":3,"losses":13,"wins":0},"google/gemma-4-31b-it":{"draws":1,"losses":4,"wins":9},"gpt-4.1":{"draws":5,"losses":5,"wins":2},"gpt-5":{"draws":8,"losses":17,"wins":3},"gpt-5.4":{"draws":4,"losses":5,"wins":5},"gpt-5.4-mini":{"draws":17,"losses":11,"wins":12},"gpt-5.4-nano":{"draws":10,"losses":14,"wins":16},"gpt-5.5":{"draws":7,"losses":25,"wins":20},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":8},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":1,"wins":0},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"gpt-6-luna":{"draws":0,"losses":1,"wins":3},"gpt-6-sol":{"draws":1,"losses":7,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":12,"losses":14,"wins":6},"meituan/longcat-2.0":{"draws":14,"losses":7,"wins":31},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":10},"meta/muse-spark-1.2":{"draws":5,"losses":6,"wins":1},"meta/muse-spark-1.3":{"draws":1,"losses":6,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":9,"wins":11},"mistralai/mistral-medium-3-5":{"draws":3,"losses":1,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":5,"wins":5},"moonshotai/kimi-k3":{"draws":9,"losses":4,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":4,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":12,"wins":9},"o3":{"draws":9,"losses":10,"wins":19},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":16,"losses":16,"wins":8},"qwen/qwen3.7-max":{"draws":10,"losses":8,"wins":16},"qwen/qwen3.7-plus":{"draws":6,"losses":8,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":10,"wins":1},"qwen/qwen3.8-27b":{"draws":1,"losses":9,"wins":4},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":6,"losses":6,"wins":2},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":11,"losses":16,"wins":19},"stepfun/step-3.7-flash":{"draws":11,"losses":2,"wins":11},"tencent/hy3-preview":{"draws":5,"losses":7,"wins":12},"tencent/hy4-preview":{"draws":3,"losses":5,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":8,"wins":13},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":6,"losses":18,"wins":6},"x-ai/grok-4.6":{"draws":3,"losses":8,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":16},"xiaomi/mimo-v2.5":{"draws":27,"losses":20,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":8,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":17,"losses":15,"wins":20},"z-ai/glm-5.3":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":6,"wins":0},"z-ai/glm-5.3-flashx":{"draws":6,"losses":2,"wins":0}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":8,"wins":14},"claude-fable-5":{"draws":16,"losses":17,"wins":13},"claude-fable-5-1":{"draws":0,"losses":48,"wins":6},"claude-opus-4-5":{"draws":24,"losses":12,"wins":40},"claude-opus-4-8":{"draws":1,"losses":2,"wins":1},"claude-opus-5":{"draws":0,"losses":22,"wins":0},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":38,"losses":18,"wins":48},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":18,"losses":6,"wins":28},"deepseek/deepseek-v4-pro":{"draws":15,"losses":10,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":10,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":14,"losses":17,"wins":17},"google/gemini-3.5-flash-lite":{"draws":57,"losses":22,"wins":81},"google/gemini-3.6-flash":{"draws":48,"losses":51,"wins":55},"google/gemini-3.8-flash":{"draws":20,"losses":19,"wins":17},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":4,"wins":6},"gpt-5.4":{"draws":25,"losses":21,"wins":35},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":6},"gpt-5.5":{"draws":6,"losses":10,"wins":4},"gpt-5.6-luna":{"draws":38,"losses":16,"wins":46},"gpt-5.6-sol":{"draws":17,"losses":57,"wins":30},"gpt-5.6-terra":{"draws":22,"losses":7,"wins":21},"gpt-6-astra":{"draws":7,"losses":32,"wins":9},"gpt-6-luna":{"draws":1,"losses":1,"wins":4},"gpt-6-sol":{"draws":1,"losses":15,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":20,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":5,"losses":8,"wins":13},"meituan/longcat-2.0":{"draws":22,"losses":8,"wins":24},"meta/muse-glimmer-30b":{"draws":16,"losses":3,"wins":15},"meta/muse-spark-1.2":{"draws":22,"losses":12,"wins":32},"meta/muse-spark-1.3":{"draws":13,"losses":9,"wins":16},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":3},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":24,"losses":21,"wins":43},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":5},"o3":{"draws":12,"losses":17,"wins":63},"openai/gpt-oss-120b":{"draws":29,"losses":8,"wins":13},"poolside/laguna-s-2.1":{"draws":20,"losses":5,"wins":21},"qwen/qwen3.7-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":3,"losses":1,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":28,"wins":15},"qwen/qwen3.8-27b":{"draws":9,"losses":4,"wins":11},"qwen/qwen3.8-flash":{"draws":7,"losses":10,"wins":13},"qwen/qwen3.8-max":{"draws":22,"losses":22,"wins":14},"qwen/qwen3.8-max-0902":{"draws":4,"losses":6,"wins":8},"stealth/ox-alpha":{"draws":49,"losses":40,"wins":55},"stepfun/step-3.7-flash":{"draws":5,"losses":4,"wins":11},"tencent/hy3-preview":{"draws":8,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":12,"losses":15,"wins":15},"thinkingmachines/inkling":{"draws":11,"losses":13,"wins":28},"thinkingmachines/inkling-small":{"draws":31,"losses":4,"wins":22},"x-ai/grok-4.5":{"draws":23,"losses":28,"wins":29},"x-ai/grok-4.6":{"draws":21,"losses":11,"wins":14},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":5,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":9,"wins":19},"z-ai/glm-5.3":{"draws":16,"losses":23,"wins":17},"z-ai/glm-5.3-flash":{"draws":14,"losses":19,"wins":17},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":0}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":3,"wins":4},"claude-fable-5":{"draws":4,"losses":11,"wins":3},"claude-fable-5-1":{"draws":0,"losses":14,"wins":0},"claude-opus-4-5":{"draws":27,"losses":33,"wins":30},"claude-opus-4-8":{"draws":8,"losses":20,"wins":24},"claude-opus-5":{"draws":11,"losses":58,"wins":9},"claude-opus-5-5":{"draws":2,"losses":12,"wins":0},"claude-sonnet-5":{"draws":4,"losses":5,"wins":7},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":14,"losses":5,"wins":21},"deepseek/deepseek-v4-pro":{"draws":4,"losses":1,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":0,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":4,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":15},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":9},"google/gemini-3.5-flash-lite":{"draws":17,"losses":6,"wins":29},"google/gemini-3.6-flash":{"draws":10,"losses":25,"wins":14},"google/gemini-3.8-flash":{"draws":5,"losses":9,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":15},"gpt-4.1":{"draws":10,"losses":4,"wins":10},"gpt-5":{"draws":13,"losses":7,"wins":20},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":2,"wins":12},"gpt-5.4-nano":{"draws":14,"losses":26,"wins":22},"gpt-5.5":{"draws":24,"losses":15,"wins":5},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":15,"wins":3},"gpt-5.6-terra":{"draws":2,"losses":7,"wins":1},"gpt-6-astra":{"draws":1,"losses":7,"wins":0},"gpt-6-luna":{"draws":3,"losses":1,"wins":2},"gpt-6-sol":{"draws":2,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":7,"losses":1,"wins":12},"meituan/longcat-2.0":{"draws":16,"losses":9,"wins":31},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":5},"meta/muse-spark-1.2":{"draws":2,"losses":3,"wins":9},"meta/muse-spark-1.3":{"draws":7,"losses":9,"wins":2},"minimax/minimax-m3":{"draws":16,"losses":6,"wins":24},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":9,"wins":6},"moonshotai/kimi-k3":{"draws":8,"losses":3,"wins":13},"nex-agi/nex-n2-pro":{"draws":10,"losses":1,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":23,"losses":11,"wins":20},"o3":{"draws":5,"losses":12,"wins":15},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":3},"poolside/laguna-s-2.1":{"draws":20,"losses":10,"wins":20},"qwen/qwen3.7-max":{"draws":12,"losses":14,"wins":12},"qwen/qwen3.7-plus":{"draws":12,"losses":10,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.8-27b":{"draws":2,"losses":6,"wins":2},"qwen/qwen3.8-flash":{"draws":1,"losses":4,"wins":1},"qwen/qwen3.8-max":{"draws":4,"losses":6,"wins":6},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":4},"stealth/ox-alpha":{"draws":11,"losses":18,"wins":23},"stepfun/step-3.7-flash":{"draws":8,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":7,"losses":2,"wins":7},"tencent/hy4-preview":{"draws":6,"losses":4,"wins":8},"thinkingmachines/inkling":{"draws":12,"losses":12,"wins":12},"thinkingmachines/inkling-small":{"draws":8,"losses":1,"wins":3},"x-ai/grok-4.5":{"draws":5,"losses":16,"wins":5},"x-ai/grok-4.6":{"draws":2,"losses":14,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":18},"xiaomi/mimo-v2.5":{"draws":38,"losses":13,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":31,"losses":19,"wins":14},"z-ai/glm-5.3":{"draws":1,"losses":12,"wins":1},"z-ai/glm-5.3-flash":{"draws":4,"losses":6,"wins":0},"z-ai/glm-5.3-flashx":{"draws":0,"losses":7,"wins":5}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":3,"wins":6},"claude-fable-5":{"draws":1,"losses":12,"wins":5},"claude-fable-5-1":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":30,"losses":39,"wins":47},"claude-opus-4-8":{"draws":14,"losses":37,"wins":21},"claude-opus-5":{"draws":10,"losses":72,"wins":22},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":1,"losses":9,"wins":10},"cohere/north-mini-code":{"draws":15,"losses":15,"wins":18},"deepseek/deepseek-v4-flash":{"draws":13,"losses":12,"wins":19},"deepseek/deepseek-v4-pro":{"draws":2,"losses":14,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":11,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":3},"google/gemini-3.1-flash-lite":{"draws":10,"losses":13,"wins":47},"google/gemini-3.5-flash":{"draws":8,"losses":20,"wins":14},"google/gemini-3.5-flash-lite":{"draws":3,"losses":35,"wins":14},"google/gemini-3.6-flash":{"draws":11,"losses":28,"wins":19},"google/gemini-3.8-flash":{"draws":7,"losses":13,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":19,"wins":17},"gpt-4.1":{"draws":2,"losses":7,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":11,"losses":18,"wins":25},"gpt-5.4":{"draws":3,"losses":10,"wins":5},"gpt-5.4-mini":{"draws":10,"losses":21,"wins":33},"gpt-5.4-nano":{"draws":13,"losses":31,"wins":38},"gpt-5.5":{"draws":20,"losses":33,"wins":23},"gpt-5.6-luna":{"draws":6,"losses":7,"wins":15},"gpt-5.6-sol":{"draws":0,"losses":18,"wins":2},"gpt-5.6-terra":{"draws":4,"losses":9,"wins":9},"gpt-6-astra":{"draws":1,"losses":25,"wins":0},"gpt-6-luna":{"draws":10,"losses":0,"wins":8},"gpt-6-sol":{"draws":0,"losses":10,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":4,"wins":6},"inclusionai/ling-3.0-flash":{"draws":19,"losses":10,"wins":9},"meituan/longcat-2.0":{"draws":14,"losses":24,"wins":46},"meta/muse-glimmer-30b":{"draws":2,"losses":4,"wins":4},"meta/muse-spark-1.2":{"draws":2,"losses":9,"wins":7},"meta/muse-spark-1.3":{"draws":6,"losses":13,"wins":5},"minimax/minimax-m3":{"draws":14,"losses":9,"wins":25},"mistralai/mistral-medium-3-5":{"draws":3,"losses":4,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":14,"wins":12},"moonshotai/kimi-k3":{"draws":8,"losses":15,"wins":5},"nex-agi/nex-n2-pro":{"draws":8,"losses":8,"wins":30},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":28,"wins":16},"o3":{"draws":4,"losses":32,"wins":38},"openai/gpt-oss-120b":{"draws":0,"losses":10,"wins":6},"poolside/laguna-s-2.1":{"draws":18,"losses":26,"wins":16},"qwen/qwen3.7-max":{"draws":8,"losses":19,"wins":15},"qwen/qwen3.7-plus":{"draws":14,"losses":27,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":20,"wins":2},"qwen/qwen3.8-27b":{"draws":2,"losses":19,"wins":5},"qwen/qwen3.8-flash":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-max":{"draws":3,"losses":11,"wins":4},"qwen/qwen3.8-max-0902":{"draws":4,"losses":7,"wins":1},"stealth/ox-alpha":{"draws":7,"losses":46,"wins":13},"stepfun/step-3.7-flash":{"draws":16,"losses":3,"wins":35},"tencent/hy3-preview":{"draws":2,"losses":6,"wins":6},"tencent/hy4-preview":{"draws":1,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":12,"wins":35},"thinkingmachines/inkling-small":{"draws":9,"losses":7,"wins":8},"x-ai/grok-4.5":{"draws":4,"losses":23,"wins":23},"x-ai/grok-4.6":{"draws":3,"losses":15,"wins":6},"x-ai/grok-4.7":{"draws":2,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":10,"wins":19},"xiaomi/mimo-v2.5":{"draws":40,"losses":50,"wins":68},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":23,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":24,"losses":41,"wins":41},"z-ai/glm-5.3":{"draws":3,"losses":22,"wins":3},"z-ai/glm-5.3-flash":{"draws":1,"losses":8,"wins":1},"z-ai/glm-5.3-flashx":{"draws":3,"losses":12,"wins":3}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":4},"claude-fable-5":{"draws":1,"losses":7,"wins":4},"claude-fable-5-1":{"draws":3,"losses":11,"wins":2},"claude-opus-4-5":{"draws":33,"losses":20,"wins":23},"claude-opus-4-8":{"draws":22,"losses":16,"wins":22},"claude-opus-5":{"draws":12,"losses":61,"wins":17},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":4},"cohere/north-mini-code":{"draws":9,"losses":1,"wins":10},"deepseek/deepseek-v4-flash":{"draws":16,"losses":2,"wins":14},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":5,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":0,"wins":4},"google/gemini-3.1-flash-lite":{"draws":12,"losses":4,"wins":14},"google/gemini-3.5-flash":{"draws":8,"losses":7,"wins":13},"google/gemini-3.5-flash-lite":{"draws":18,"losses":1,"wins":9},"google/gemini-3.6-flash":{"draws":15,"losses":16,"wins":15},"google/gemini-3.8-flash":{"draws":6,"losses":5,"wins":1},"google/gemma-4-31b-it":{"draws":9,"losses":0,"wins":15},"gpt-4.1":{"draws":7,"losses":3,"wins":8},"gpt-5":{"draws":11,"losses":14,"wins":19},"gpt-5.4":{"draws":3,"losses":3,"wins":6},"gpt-5.4-mini":{"draws":27,"losses":5,"wins":16},"gpt-5.4-nano":{"draws":22,"losses":32,"wins":20},"gpt-5.5":{"draws":13,"losses":12,"wins":13},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":9},"gpt-5.6-sol":{"draws":5,"losses":3,"wins":6},"gpt-5.6-terra":{"draws":5,"losses":1,"wins":0},"gpt-6-astra":{"draws":1,"losses":7,"wins":2},"gpt-6-luna":{"draws":0,"losses":2,"wins":4},"gpt-6-sol":{"draws":0,"losses":8,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":2,"wins":1},"inclusionai/ling-3.0-flash":{"draws":13,"losses":4,"wins":11},"meituan/longcat-2.0":{"draws":10,"losses":14,"wins":22},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":7},"meta/muse-spark-1.2":{"draws":4,"losses":6,"wins":4},"meta/muse-spark-1.3":{"draws":2,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":11,"losses":2,"wins":17},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":13,"losses":3,"wins":6},"moonshotai/kimi-k3":{"draws":10,"losses":10,"wins":4},"nex-agi/nex-n2-pro":{"draws":6,"losses":5,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":19,"losses":2,"wins":27},"o3":{"draws":9,"losses":8,"wins":7},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":17,"losses":9,"wins":12},"qwen/qwen3.7-max":{"draws":15,"losses":7,"wins":12},"qwen/qwen3.7-plus":{"draws":16,"losses":6,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":0,"wins":6},"qwen/qwen3.8-27b":{"draws":1,"losses":4,"wins":7},"qwen/qwen3.8-flash":{"draws":5,"losses":3,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":8,"wins":6},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":19,"losses":18,"wins":7},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":20},"tencent/hy3-preview":{"draws":9,"losses":4,"wins":11},"tencent/hy4-preview":{"draws":5,"losses":5,"wins":6},"thinkingmachines/inkling":{"draws":13,"losses":13,"wins":12},"thinkingmachines/inkling-small":{"draws":2,"losses":3,"wins":9},"x-ai/grok-4.5":{"draws":9,"losses":18,"wins":9},"x-ai/grok-4.6":{"draws":2,"losses":7,"wins":3},"x-ai/grok-4.7":{"draws":1,"losses":4,"wins":7},"x-ai/grok-build-0.1":{"draws":19,"losses":5,"wins":6},"xiaomi/mimo-v2.5":{"draws":28,"losses":11,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":10,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":31,"losses":16,"wins":21},"z-ai/glm-5.3":{"draws":3,"losses":10,"wins":3},"z-ai/glm-5.3-flash":{"draws":6,"losses":3,"wins":7},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":0}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":17,"wins":16},"claude-fable-5":{"draws":13,"losses":28,"wins":1},"claude-fable-5-1":{"draws":5,"losses":31,"wins":0},"claude-opus-4-5":{"draws":31,"losses":30,"wins":19},"claude-opus-4-8":{"draws":6,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":22,"wins":6},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":37,"losses":34,"wins":27},"deepseek/deepseek-v4-flash":{"draws":22,"losses":18,"wins":20},"deepseek/deepseek-v4-pro":{"draws":16,"losses":17,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":19,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":5,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":25,"losses":21,"wins":10},"google/gemini-3.5-flash-lite":{"draws":60,"losses":43,"wins":77},"google/gemini-3.6-flash":{"draws":45,"losses":74,"wins":39},"google/gemini-3.8-flash":{"draws":16,"losses":29,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":3,"losses":1,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":1,"losses":9,"wins":2},"gpt-5.4":{"draws":33,"losses":54,"wins":15},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":4,"wins":5},"gpt-5.5":{"draws":3,"losses":4,"wins":5},"gpt-5.6-luna":{"draws":38,"losses":15,"wins":24},"gpt-5.6-sol":{"draws":20,"losses":68,"wins":12},"gpt-5.6-terra":{"draws":15,"losses":17,"wins":18},"gpt-6-astra":{"draws":8,"losses":26,"wins":0},"gpt-6-luna":{"draws":1,"losses":8,"wins":1},"gpt-6-sol":{"draws":2,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":16,"losses":2,"wins":20},"inclusionai/ling-3.0-flash":{"draws":12,"losses":8,"wins":14},"meituan/longcat-2.0":{"draws":17,"losses":11,"wins":28},"meta/muse-glimmer-30b":{"draws":21,"losses":8,"wins":23},"meta/muse-spark-1.2":{"draws":19,"losses":33,"wins":16},"meta/muse-spark-1.3":{"draws":12,"losses":19,"wins":9},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":2},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":29,"losses":46,"wins":17},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":1},"o3":{"draws":18,"losses":38,"wins":40},"openai/gpt-oss-120b":{"draws":19,"losses":9,"wins":22},"poolside/laguna-s-2.1":{"draws":22,"losses":6,"wins":24},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":19,"wins":9},"qwen/qwen3.8-27b":{"draws":7,"losses":9,"wins":10},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":12},"qwen/qwen3.8-max":{"draws":20,"losses":21,"wins":12},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":61,"losses":53,"wins":42},"stepfun/step-3.7-flash":{"draws":7,"losses":7,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":12,"losses":34,"wins":4},"thinkingmachines/inkling":{"draws":29,"losses":13,"wins":32},"thinkingmachines/inkling-small":{"draws":24,"losses":12,"wins":24},"x-ai/grok-4.5":{"draws":18,"losses":26,"wins":16},"x-ai/grok-4.6":{"draws":17,"losses":24,"wins":7},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":13,"losses":1,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":25,"losses":14,"wins":17},"z-ai/glm-5.3":{"draws":12,"losses":26,"wins":6},"z-ai/glm-5.3-flash":{"draws":16,"losses":19,"wins":11}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":10,"wins":24},"claude-fable-5":{"draws":9,"losses":20,"wins":19},"claude-fable-5-1":{"draws":8,"losses":50,"wins":4},"claude-opus-4-5":{"draws":17,"losses":13,"wins":52},"claude-opus-4-8":{"draws":1,"losses":8,"wins":7},"claude-opus-5":{"draws":11,"losses":26,"wins":9},"claude-opus-5-5":{"draws":0,"losses":7,"wins":1},"claude-sonnet-5":{"draws":14,"losses":18,"wins":73},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":31},"deepseek/deepseek-v4-pro":{"draws":2,"losses":12,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":10,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":7},"google/gemini-3.5-flash":{"draws":5,"losses":11,"wins":24},"google/gemini-3.5-flash-lite":{"draws":17,"losses":18,"wins":101},"google/gemini-3.6-flash":{"draws":20,"losses":45,"wins":71},"google/gemini-3.8-flash":{"draws":5,"losses":27,"wins":24},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":4},"gpt-5.4":{"draws":18,"losses":24,"wins":48},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":4},"gpt-5.5":{"draws":4,"losses":5,"wins":3},"gpt-5.6-luna":{"draws":10,"losses":18,"wins":52},"gpt-5.6-sol":{"draws":14,"losses":45,"wins":13},"gpt-5.6-terra":{"draws":15,"losses":9,"wins":28},"gpt-6-astra":{"draws":6,"losses":43,"wins":3},"gpt-6-luna":{"draws":2,"losses":1,"wins":3},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":22},"inclusionai/ling-3.0-flash":{"draws":1,"losses":4,"wins":21},"meituan/longcat-2.0":{"draws":8,"losses":8,"wins":28},"meta/muse-glimmer-30b":{"draws":0,"losses":1,"wins":19},"meta/muse-spark-1.2":{"draws":6,"losses":15,"wins":49},"meta/muse-spark-1.3":{"draws":9,"losses":14,"wins":13},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":3},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":25,"losses":22,"wins":39},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":6},"o3":{"draws":9,"losses":14,"wins":63},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":16},"poolside/laguna-s-2.1":{"draws":10,"losses":1,"wins":47},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":12,"wins":36},"qwen/qwen3.8-27b":{"draws":5,"losses":10,"wins":13},"qwen/qwen3.8-flash":{"draws":4,"losses":6,"wins":20},"qwen/qwen3.8-max":{"draws":12,"losses":13,"wins":21},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":5},"stealth/ox-alpha":{"draws":22,"losses":44,"wins":87},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":3},"tencent/hy4-preview":{"draws":4,"losses":11,"wins":29},"thinkingmachines/inkling":{"draws":8,"losses":4,"wins":38},"thinkingmachines/inkling-small":{"draws":5,"losses":12,"wins":21},"x-ai/grok-4.5":{"draws":9,"losses":30,"wins":39},"x-ai/grok-4.6":{"draws":8,"losses":24,"wins":18},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":1,"losses":1,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":0,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":7,"losses":8,"wins":49},"z-ai/glm-5.3":{"draws":13,"losses":16,"wins":19},"z-ai/glm-5.3-flash":{"draws":13,"losses":19,"wins":22},"z-ai/glm-5.3-flashx":{"draws":1,"losses":1,"wins":4}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":9,"wins":16},"claude-fable-5":{"draws":10,"losses":34,"wins":10},"claude-fable-5-1":{"draws":4,"losses":48,"wins":2},"claude-opus-4-5":{"draws":16,"losses":16,"wins":12},"claude-opus-4-8":{"draws":8,"losses":7,"wins":1},"claude-opus-5":{"draws":2,"losses":27,"wins":1},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":12,"losses":15,"wins":23},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":27,"losses":13,"wins":18},"deepseek/deepseek-v4-pro":{"draws":17,"losses":18,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":15,"wins":18},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":12},"google/gemini-3.5-flash":{"draws":12,"losses":15,"wins":23},"google/gemini-3.5-flash-lite":{"draws":23,"losses":16,"wins":41},"google/gemini-3.6-flash":{"draws":19,"losses":39,"wins":22},"google/gemini-3.8-flash":{"draws":16,"losses":15,"wins":19},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":9},"gpt-4.1":{"draws":10,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":1,"losses":0,"wins":5},"gpt-5.4":{"draws":15,"losses":23,"wins":8},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":12},"gpt-5.5":{"draws":3,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":20,"losses":22,"wins":14},"gpt-5.6-sol":{"draws":16,"losses":30,"wins":10},"gpt-5.6-terra":{"draws":10,"losses":13,"wins":11},"gpt-6-astra":{"draws":6,"losses":49,"wins":3},"gpt-6-luna":{"draws":2,"losses":1,"wins":5},"gpt-6-sol":{"draws":0,"losses":1,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":9,"losses":1,"wins":18},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":15},"meituan/longcat-2.0":{"draws":8,"losses":9,"wins":23},"meta/muse-glimmer-30b":{"draws":16,"losses":6,"wins":16},"meta/muse-spark-1.2":{"draws":8,"losses":14,"wins":16},"meta/muse-spark-1.3":{"draws":14,"losses":27,"wins":17},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":5,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":27,"wins":17},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":4,"wins":7},"o3":{"draws":8,"losses":19,"wins":31},"openai/gpt-oss-120b":{"draws":13,"losses":6,"wins":29},"poolside/laguna-s-2.1":{"draws":8,"losses":5,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":24,"wins":9},"qwen/qwen3.8-27b":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-flash":{"draws":8,"losses":14,"wins":6},"qwen/qwen3.8-max":{"draws":22,"losses":15,"wins":11},"qwen/qwen3.8-max-0902":{"draws":6,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":47,"losses":63,"wins":42},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":7},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":3},"tencent/hy4-preview":{"draws":10,"losses":19,"wins":9},"thinkingmachines/inkling":{"draws":10,"losses":4,"wins":14},"thinkingmachines/inkling-small":{"draws":14,"losses":10,"wins":24},"x-ai/grok-4.5":{"draws":9,"losses":27,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":29,"wins":15},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.5":{"draws":7,"losses":2,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":23,"losses":15,"wins":24},"z-ai/glm-5.3":{"draws":9,"losses":29,"wins":8},"z-ai/glm-5.3-flash":{"draws":10,"losses":21,"wins":13},"z-ai/glm-5.3-flashx":{"draws":1,"losses":1,"wins":6}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":24},"claude-fable-5":{"draws":4,"losses":10,"wins":40},"claude-fable-5-1":{"draws":6,"losses":23,"wins":33},"claude-opus-4-5":{"draws":6,"losses":0,"wins":42},"claude-opus-4-8":{"draws":0,"losses":0,"wins":12},"claude-opus-5":{"draws":3,"losses":7,"wins":16},"claude-opus-5-5":{"draws":0,"losses":4,"wins":4},"claude-sonnet-5":{"draws":2,"losses":0,"wins":44},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":32},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":37},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":0,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":6,"losses":5,"wins":39},"google/gemini-3.5-flash-lite":{"draws":4,"losses":0,"wins":42},"google/gemini-3.6-flash":{"draws":5,"losses":9,"wins":60},"google/gemini-3.8-flash":{"draws":7,"losses":3,"wins":52},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":0,"wins":6},"gpt-5.4":{"draws":5,"losses":6,"wins":37},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":11},"gpt-5.5":{"draws":1,"losses":2,"wins":11},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":28},"gpt-5.6-sol":{"draws":6,"losses":8,"wins":40},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":46},"gpt-6-astra":{"draws":4,"losses":23,"wins":9},"gpt-6-luna":{"draws":2,"losses":1,"wins":5},"gpt-6-sol":{"draws":0,"losses":0,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":5,"losses":0,"wins":11},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":7},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":18},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":20},"meta/muse-spark-1.2":{"draws":7,"losses":0,"wins":29},"meta/muse-spark-1.3":{"draws":6,"losses":3,"wins":37},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":12},"moonshotai/kimi-k3":{"draws":10,"losses":3,"wins":31},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":4},"o3":{"draws":0,"losses":0,"wins":46},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":14},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":22},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":10},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":2,"wins":36},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":28},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":26},"qwen/qwen3.8-max":{"draws":6,"losses":0,"wins":40},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":6},"stealth/ox-alpha":{"draws":32,"losses":12,"wins":120},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":12},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":3,"losses":3,"wins":36},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":26},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":20},"x-ai/grok-4.5":{"draws":0,"losses":3,"wins":43},"x-ai/grok-4.6":{"draws":7,"losses":6,"wins":43},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":14},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":1},"z-ai/glm-5.2":{"draws":4,"losses":2,"wins":50},"z-ai/glm-5.3":{"draws":10,"losses":8,"wins":38},"z-ai/glm-5.3-flash":{"draws":7,"losses":2,"wins":37},"z-ai/glm-5.3-flashx":{"draws":0,"losses":1,"wins":5}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":4,"wins":3},"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-fable-5-1":{"draws":1,"losses":5,"wins":0},"claude-opus-4-5":{"draws":5,"losses":7,"wins":4},"claude-opus-4-8":{"draws":2,"losses":3,"wins":1},"claude-opus-5":{"draws":4,"losses":10,"wins":0},"claude-opus-5-5":{"draws":5,"losses":47,"wins":0},"claude-sonnet-5":{"draws":0,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":6,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":3,"losses":7,"wins":6},"google/gemini-3.5-flash-lite":{"draws":7,"losses":5,"wins":10},"google/gemini-3.6-flash":{"draws":6,"losses":13,"wins":1},"google/gemini-3.8-flash":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":3,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":9,"losses":3,"wins":4},"gpt-5.5":{"draws":6,"losses":6,"wins":0},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":13,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":2,"wins":3},"gpt-6-astra":{"draws":1,"losses":12,"wins":1},"gpt-6-luna":{"draws":8,"losses":11,"wins":11},"gpt-6-sol":{"draws":9,"losses":35,"wins":4},"inception/mercury-2.5-preview":{"draws":5,"losses":1,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":4},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":1},"meta/muse-spark-1.2":{"draws":1,"losses":0,"wins":1},"meta/muse-spark-1.3":{"draws":2,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":1,"wins":3},"o3":{"draws":6,"losses":4,"wins":4},"openai/gpt-oss-120b":{"draws":5,"losses":4,"wins":3},"poolside/laguna-s-2.1":{"draws":5,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":5,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.8-max":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-max-0902":{"draws":10,"losses":4,"wins":4},"stealth/ox-alpha":{"draws":9,"losses":7,"wins":6},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":2,"losses":4,"wins":2},"tencent/hy4-preview":{"draws":1,"losses":3,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":2},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":5,"wins":0},"x-ai/grok-4.6":{"draws":1,"losses":6,"wins":1},"x-ai/grok-4.7":{"draws":3,"losses":23,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":2,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":5,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":12,"wins":6},"z-ai/glm-5.2":{"draws":8,"losses":8,"wins":2},"z-ai/glm-5.3":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":3,"losses":8,"wins":1},"z-ai/glm-5.3-flashx":{"draws":8,"losses":23,"wins":5}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":4},"claude-fable-5":{"draws":2,"losses":1,"wins":5},"claude-fable-5-1":{"draws":0,"losses":2,"wins":2},"claude-opus-4-5":{"draws":4,"losses":1,"wins":9},"claude-opus-4-8":{"draws":1,"losses":1,"wins":2},"claude-opus-5":{"draws":2,"losses":5,"wins":9},"claude-opus-5-5":{"draws":5,"losses":35,"wins":12},"claude-sonnet-5":{"draws":3,"losses":2,"wins":13},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":1},"deepseek/deepseek-v4-flash":{"draws":3,"losses":0,"wins":9},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":0,"wins":12},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":3,"losses":0,"wins":7},"google/gemini-3.5-flash-lite":{"draws":6,"losses":1,"wins":21},"google/gemini-3.6-flash":{"draws":2,"losses":3,"wins":17},"google/gemini-3.8-flash":{"draws":1,"losses":2,"wins":1},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-5":{"draws":1,"losses":0,"wins":7},"gpt-5.4":{"draws":2,"losses":2,"wins":6},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":4},"gpt-5.5":{"draws":2,"losses":1,"wins":9},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":2},"gpt-6-astra":{"draws":1,"losses":6,"wins":1},"gpt-6-luna":{"draws":8,"losses":7,"wins":31},"gpt-6-sol":{"draws":6,"losses":12,"wins":14},"inception/mercury-2.5-preview":{"draws":1,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":8},"meituan/longcat-2.0":{"draws":2,"losses":0,"wins":12},"meta/muse-spark-1.2":{"draws":1,"losses":0,"wins":3},"meta/muse-spark-1.3":{"draws":1,"losses":0,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":6,"wins":3},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":6},"o3":{"draws":0,"losses":0,"wins":4},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":3,"losses":0,"wins":11},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-27b":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-flash":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":6},"qwen/qwen3.8-max-0902":{"draws":3,"losses":3,"wins":4},"stealth/ox-alpha":{"draws":2,"losses":4,"wins":16},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":7},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":4},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":10},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":3,"wins":5},"x-ai/grok-4.6":{"draws":3,"losses":0,"wins":5},"x-ai/grok-4.7":{"draws":4,"losses":10,"wins":16},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":4,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":6,"wins":10},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":18},"z-ai/glm-5.3":{"draws":0,"losses":10,"wins":2},"z-ai/glm-5.3-flash":{"draws":1,"losses":3,"wins":8},"z-ai/glm-5.3-flashx":{"draws":7,"losses":10,"wins":23}},"ibm-granite/granite-4.2-8b":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":10,"wins":0},"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":2,"losses":12,"wins":0},"claude-opus-4-8":{"draws":2,"losses":2,"wins":0},"claude-opus-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":0,"losses":12,"wins":0},"deepseek/deepseek-v4-flash":{"draws":9,"losses":7,"wins":0},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":4,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":1,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":0},"google/gemini-3.5-flash":{"draws":6,"losses":10,"wins":0},"google/gemini-3.5-flash-lite":{"draws":14,"losses":8,"wins":0},"google/gemini-3.6-flash":{"draws":3,"losses":17,"wins":0},"google/gemini-3.8-flash":{"draws":2,"losses":10,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-4.1":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":0,"losses":6,"wins":0},"gpt-5.4":{"draws":4,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":0,"losses":3,"wins":1},"gpt-5.5":{"draws":0,"losses":6,"wins":0},"gpt-5.6-luna":{"draws":9,"losses":6,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":6,"wins":0},"gpt-6-astra":{"draws":0,"losses":8,"wins":0},"gpt-6-luna":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":6,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":4,"wins":0},"meituan/longcat-2.0":{"draws":4,"losses":4,"wins":2},"meta/muse-glimmer-30b":{"draws":8,"losses":8,"wins":0},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":0},"meta/muse-spark-1.3":{"draws":1,"losses":7,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":1,"losses":9,"wins":0},"o3":{"draws":4,"losses":14,"wins":0},"openai/gpt-oss-120b":{"draws":8,"losses":10,"wins":0},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":7,"wins":0},"qwen/qwen3.8-27b":{"draws":4,"losses":4,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.8-max":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":10,"losses":18,"wins":0},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":0},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":8,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":10,"wins":0},"thinkingmachines/inkling-small":{"draws":8,"losses":8,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":0,"losses":8,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":8,"losses":4,"wins":2},"z-ai/glm-5.3":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":2,"wins":0},"z-ai/glm-5.3-flashx":{"draws":0,"losses":4,"wins":0}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":17,"wins":8},"claude-fable-5":{"draws":8,"losses":14,"wins":0},"claude-fable-5-1":{"draws":3,"losses":7,"wins":0},"claude-opus-4-5":{"draws":11,"losses":28,"wins":1},"claude-opus-4-8":{"draws":4,"losses":10,"wins":0},"claude-opus-5":{"draws":2,"losses":22,"wins":0},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":19,"losses":18,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":2},"deepseek/deepseek-v4-flash":{"draws":23,"losses":16,"wins":1},"deepseek/deepseek-v4-pro":{"draws":16,"losses":16,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":14,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":10,"losses":17,"wins":3},"google/gemini-3.5-flash-lite":{"draws":37,"losses":34,"wins":11},"google/gemini-3.6-flash":{"draws":17,"losses":25,"wins":2},"google/gemini-3.8-flash":{"draws":13,"losses":10,"wins":1},"google/gemma-4-31b-it":{"draws":3,"losses":8,"wins":3},"gpt-5":{"draws":0,"losses":8,"wins":0},"gpt-5.4":{"draws":14,"losses":12,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":11,"wins":1},"gpt-5.5":{"draws":1,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":23,"losses":14,"wins":5},"gpt-5.6-sol":{"draws":2,"losses":14,"wins":0},"gpt-5.6-terra":{"draws":16,"losses":20,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":1,"losses":4,"wins":1},"gpt-6-sol":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":14,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":4,"losses":5,"wins":1},"meituan/longcat-2.0":{"draws":9,"losses":9,"wins":7},"meta/muse-glimmer-30b":{"draws":20,"losses":10,"wins":4},"meta/muse-spark-1.2":{"draws":9,"losses":9,"wins":2},"meta/muse-spark-1.3":{"draws":8,"losses":16,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":2},"mistralai/mistral-medium-3-5":{"draws":15,"losses":7,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":20,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":6,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":2,"wins":3},"o3":{"draws":7,"losses":24,"wins":5},"openai/gpt-oss-120b":{"draws":19,"losses":15,"wins":4},"poolside/laguna-s-2.1":{"draws":8,"losses":5,"wins":7},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":4,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":16,"wins":3},"qwen/qwen3.8-27b":{"draws":3,"losses":11,"wins":2},"qwen/qwen3.8-flash":{"draws":12,"losses":7,"wins":3},"qwen/qwen3.8-max":{"draws":14,"losses":10,"wins":2},"qwen/qwen3.8-max-0902":{"draws":1,"losses":3,"wins":0},"stealth/ox-alpha":{"draws":26,"losses":46,"wins":8},"stepfun/step-3.7-flash":{"draws":3,"losses":8,"wins":3},"tencent/hy3-preview":{"draws":7,"losses":4,"wins":3},"tencent/hy4-preview":{"draws":13,"losses":12,"wins":3},"thinkingmachines/inkling":{"draws":20,"losses":8,"wins":4},"thinkingmachines/inkling-small":{"draws":16,"losses":15,"wins":9},"x-ai/grok-4.5":{"draws":11,"losses":13,"wins":0},"x-ai/grok-4.6":{"draws":6,"losses":19,"wins":3},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":8,"losses":10,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":22,"losses":21,"wins":5},"z-ai/glm-5.3":{"draws":10,"losses":13,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":17,"wins":3},"z-ai/glm-5.3-flashx":{"draws":4,"losses":4,"wins":0}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":13,"wins":7},"claude-fable-5":{"draws":7,"losses":10,"wins":1},"claude-fable-5-1":{"draws":0,"losses":30,"wins":0},"claude-opus-4-5":{"draws":22,"losses":36,"wins":16},"claude-opus-4-8":{"draws":12,"losses":6,"wins":0},"claude-opus-5":{"draws":8,"losses":19,"wins":1},"claude-opus-5-5":{"draws":2,"losses":10,"wins":0},"claude-sonnet-5":{"draws":21,"losses":52,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":15,"losses":16,"wins":21},"deepseek/deepseek-v4-pro":{"draws":5,"losses":19,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":11,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":8},"google/gemini-3.5-flash":{"draws":14,"losses":25,"wins":5},"google/gemini-3.5-flash-lite":{"draws":50,"losses":99,"wins":39},"google/gemini-3.6-flash":{"draws":59,"losses":69,"wins":28},"google/gemini-3.8-flash":{"draws":2,"losses":20,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":7},"gpt-4.1":{"draws":4,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":0},"gpt-5":{"draws":4,"losses":10,"wins":0},"gpt-5.4":{"draws":12,"losses":33,"wins":13},"gpt-5.4-mini":{"draws":2,"losses":5,"wins":1},"gpt-5.4-nano":{"draws":8,"losses":7,"wins":5},"gpt-5.5":{"draws":4,"losses":8,"wins":2},"gpt-5.6-luna":{"draws":24,"losses":23,"wins":25},"gpt-5.6-sol":{"draws":11,"losses":43,"wins":6},"gpt-5.6-terra":{"draws":9,"losses":23,"wins":4},"gpt-6-astra":{"draws":1,"losses":25,"wins":0},"gpt-6-luna":{"draws":3,"losses":5,"wins":0},"gpt-6-sol":{"draws":1,"losses":3,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":11},"inclusionai/ling-3.0-flash":{"draws":4,"losses":13,"wins":13},"meituan/longcat-2.0":{"draws":22,"losses":32,"wins":28},"meta/muse-glimmer-30b":{"draws":16,"losses":13,"wins":9},"meta/muse-spark-1.2":{"draws":17,"losses":15,"wins":12},"meta/muse-spark-1.3":{"draws":3,"losses":17,"wins":4},"minimax/minimax-m3":{"draws":10,"losses":5,"wins":11},"mistralai/mistral-medium-3-5":{"draws":12,"losses":7,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":18,"losses":56,"wins":20},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":12},"o3":{"draws":7,"losses":77,"wins":32},"openai/gpt-oss-120b":{"draws":9,"losses":24,"wins":7},"poolside/laguna-s-2.1":{"draws":20,"losses":22,"wins":8},"qwen/qwen3.7-max":{"draws":11,"losses":19,"wins":0},"qwen/qwen3.7-plus":{"draws":6,"losses":6,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":16,"wins":3},"qwen/qwen3.8-27b":{"draws":1,"losses":12,"wins":3},"qwen/qwen3.8-flash":{"draws":9,"losses":13,"wins":8},"qwen/qwen3.8-max":{"draws":18,"losses":18,"wins":9},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":0},"stealth/ox-alpha":{"draws":17,"losses":45,"wins":22},"stepfun/step-3.7-flash":{"draws":0,"losses":14,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":1},"tencent/hy4-preview":{"draws":7,"losses":21,"wins":4},"thinkingmachines/inkling":{"draws":30,"losses":24,"wins":26},"thinkingmachines/inkling-small":{"draws":13,"losses":24,"wins":12},"x-ai/grok-4.5":{"draws":27,"losses":50,"wins":9},"x-ai/grok-4.6":{"draws":7,"losses":16,"wins":3},"x-ai/grok-4.7":{"draws":3,"losses":1,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":8,"wins":1},"xiaomi/mimo-v2.5":{"draws":5,"losses":9,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":9,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":16,"wins":11},"z-ai/glm-5.3":{"draws":8,"losses":14,"wins":0},"z-ai/glm-5.3-flash":{"draws":3,"losses":19,"wins":2},"z-ai/glm-5.3-flashx":{"draws":1,"losses":9,"wins":0}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":25,"wins":16},"claude-fable-5":{"draws":10,"losses":28,"wins":17},"claude-fable-5-1":{"draws":1,"losses":37,"wins":2},"claude-opus-4-5":{"draws":31,"losses":90,"wins":30},"claude-opus-4-8":{"draws":8,"losses":19,"wins":7},"claude-opus-5":{"draws":10,"losses":52,"wins":10},"claude-opus-5-5":{"draws":0,"losses":7,"wins":1},"claude-sonnet-5":{"draws":44,"losses":77,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":5,"wins":17},"deepseek/deepseek-v4-flash":{"draws":29,"losses":30,"wins":11},"deepseek/deepseek-v4-pro":{"draws":21,"losses":34,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":25,"losses":33,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":17,"wins":5},"google/gemini-3.1-flash-lite":{"draws":2,"losses":5,"wins":13},"google/gemini-3.5-flash":{"draws":17,"losses":52,"wins":11},"google/gemini-3.5-flash-lite":{"draws":77,"losses":131,"wins":140},"google/gemini-3.6-flash":{"draws":76,"losses":166,"wins":43},"google/gemini-3.8-flash":{"draws":14,"losses":21,"wins":10},"google/gemma-4-31b-it":{"draws":1,"losses":11,"wins":12},"gpt-4.1":{"draws":3,"losses":7,"wins":2},"gpt-5":{"draws":7,"losses":11,"wins":2},"gpt-5.4":{"draws":39,"losses":65,"wins":19},"gpt-5.4-mini":{"draws":11,"losses":20,"wins":9},"gpt-5.4-nano":{"draws":6,"losses":17,"wins":11},"gpt-5.5":{"draws":12,"losses":18,"wins":7},"gpt-5.6-luna":{"draws":46,"losses":60,"wins":44},"gpt-5.6-sol":{"draws":21,"losses":96,"wins":15},"gpt-5.6-terra":{"draws":19,"losses":34,"wins":21},"gpt-6-astra":{"draws":3,"losses":37,"wins":2},"gpt-6-luna":{"draws":4,"losses":10,"wins":2},"gpt-6-sol":{"draws":0,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":1,"wins":4},"inception/mercury-2.5-preview":{"draws":19,"losses":11,"wins":25},"inclusionai/ling-3.0-flash":{"draws":30,"losses":21,"wins":33},"meituan/longcat-2.0":{"draws":27,"losses":28,"wins":28},"meta/muse-glimmer-30b":{"draws":24,"losses":28,"wins":20},"meta/muse-spark-1.2":{"draws":28,"losses":40,"wins":34},"meta/muse-spark-1.3":{"draws":19,"losses":29,"wins":8},"minimax/minimax-m3":{"draws":1,"losses":9,"wins":10},"mistralai/mistral-medium-3-5":{"draws":19,"losses":9,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":44,"losses":97,"wins":17},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":7,"wins":6},"o3":{"draws":21,"losses":138,"wins":53},"openai/gpt-oss-120b":{"draws":28,"losses":16,"wins":26},"poolside/laguna-s-2.1":{"draws":42,"losses":25,"wins":49},"qwen/qwen3.7-max":{"draws":2,"losses":16,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":41,"wins":10},"qwen/qwen3.8-27b":{"draws":7,"losses":25,"wins":12},"qwen/qwen3.8-flash":{"draws":19,"losses":21,"wins":8},"qwen/qwen3.8-max":{"draws":28,"losses":34,"wins":12},"qwen/qwen3.8-max-0902":{"draws":5,"losses":19,"wins":3},"stealth/ox-alpha":{"draws":52,"losses":112,"wins":28},"stepfun/step-3.7-flash":{"draws":13,"losses":28,"wins":23},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":19,"losses":37,"wins":8},"thinkingmachines/inkling":{"draws":32,"losses":55,"wins":45},"thinkingmachines/inkling-small":{"draws":20,"losses":25,"wins":32},"x-ai/grok-4.5":{"draws":35,"losses":87,"wins":26},"x-ai/grok-4.6":{"draws":15,"losses":32,"wins":13},"x-ai/grok-4.7":{"draws":2,"losses":6,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":13,"wins":4},"xiaomi/mimo-v2.5":{"draws":20,"losses":15,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":3,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":1,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":22,"losses":33,"wins":35},"z-ai/glm-5.3":{"draws":20,"losses":30,"wins":6},"z-ai/glm-5.3-flash":{"draws":10,"losses":29,"wins":17},"z-ai/glm-5.3-flashx":{"draws":8,"losses":7,"wins":2}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":19,"wins":16},"claude-fable-5":{"draws":10,"losses":10,"wins":2},"claude-fable-5-1":{"draws":1,"losses":21,"wins":0},"claude-opus-4-5":{"draws":16,"losses":22,"wins":6},"claude-opus-4-8":{"draws":2,"losses":7,"wins":1},"claude-opus-5":{"draws":1,"losses":7,"wins":2},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":19,"losses":20,"wins":5},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":32,"losses":24,"wins":6},"deepseek/deepseek-v4-pro":{"draws":15,"losses":24,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":25,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":15,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":14,"losses":19,"wins":7},"google/gemini-3.5-flash-lite":{"draws":43,"losses":37,"wins":14},"google/gemini-3.6-flash":{"draws":33,"losses":38,"wins":7},"google/gemini-3.8-flash":{"draws":11,"losses":11,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":1},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":6,"wins":1},"gpt-5.4":{"draws":10,"losses":10,"wins":6},"gpt-5.4-mini":{"draws":7,"losses":4,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":5},"gpt-5.5":{"draws":4,"losses":14,"wins":0},"gpt-5.6-luna":{"draws":19,"losses":17,"wins":12},"gpt-5.6-sol":{"draws":3,"losses":12,"wins":1},"gpt-5.6-terra":{"draws":18,"losses":19,"wins":7},"gpt-6-astra":{"draws":1,"losses":11,"wins":0},"gpt-6-luna":{"draws":0,"losses":7,"wins":1},"gpt-6-sol":{"draws":3,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":22,"losses":12,"wins":10},"inclusionai/ling-3.0-flash":{"draws":9,"losses":8,"wins":7},"meituan/longcat-2.0":{"draws":12,"losses":12,"wins":8},"meta/muse-glimmer-30b":{"draws":14,"losses":8,"wins":6},"meta/muse-spark-1.2":{"draws":7,"losses":15,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":12,"wins":2},"minimax/minimax-m3":{"draws":5,"losses":5,"wins":2},"mistralai/mistral-medium-3-5":{"draws":16,"losses":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":13,"losses":19,"wins":6},"nex-agi/nex-n2-pro":{"draws":4,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":1,"wins":3},"o3":{"draws":11,"losses":32,"wins":5},"openai/gpt-oss-120b":{"draws":26,"losses":15,"wins":11},"poolside/laguna-s-2.1":{"draws":24,"losses":11,"wins":3},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":20,"wins":2},"qwen/qwen3.8-27b":{"draws":5,"losses":17,"wins":2},"qwen/qwen3.8-flash":{"draws":14,"losses":6,"wins":6},"qwen/qwen3.8-max":{"draws":14,"losses":23,"wins":11},"qwen/qwen3.8-max-0902":{"draws":5,"losses":7,"wins":0},"stealth/ox-alpha":{"draws":46,"losses":70,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":6,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":14,"losses":19,"wins":3},"thinkingmachines/inkling":{"draws":19,"losses":9,"wins":10},"thinkingmachines/inkling-small":{"draws":29,"losses":14,"wins":21},"x-ai/grok-4.5":{"draws":8,"losses":17,"wins":3},"x-ai/grok-4.6":{"draws":16,"losses":10,"wins":6},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":5,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":3},"z-ai/glm-5.2":{"draws":28,"losses":22,"wins":10},"z-ai/glm-5.3":{"draws":4,"losses":11,"wins":3},"z-ai/glm-5.3-flash":{"draws":14,"losses":22,"wins":6},"z-ai/glm-5.3-flashx":{"draws":3,"losses":7,"wins":2}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":10,"wins":11},"claude-fable-5":{"draws":6,"losses":22,"wins":14},"claude-fable-5-1":{"draws":3,"losses":40,"wins":7},"claude-opus-4-5":{"draws":19,"losses":13,"wins":36},"claude-opus-4-8":{"draws":5,"losses":7,"wins":6},"claude-opus-5":{"draws":3,"losses":20,"wins":7},"claude-opus-5-5":{"draws":0,"losses":6,"wins":2},"claude-sonnet-5":{"draws":27,"losses":24,"wins":31},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":14,"losses":4,"wins":16},"deepseek/deepseek-v4-pro":{"draws":4,"losses":14,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":9,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":7,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":6},"google/gemini-3.5-flash":{"draws":15,"losses":14,"wins":23},"google/gemini-3.5-flash-lite":{"draws":37,"losses":19,"wins":84},"google/gemini-3.6-flash":{"draws":20,"losses":35,"wins":81},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":28},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":6},"gpt-4.1":{"draws":2,"losses":1,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":3,"wins":6},"gpt-5.4":{"draws":20,"losses":34,"wins":32},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":3},"gpt-5.5":{"draws":2,"losses":2,"wins":4},"gpt-5.6-luna":{"draws":27,"losses":11,"wins":44},"gpt-5.6-sol":{"draws":8,"losses":51,"wins":29},"gpt-5.6-terra":{"draws":20,"losses":8,"wins":20},"gpt-6-astra":{"draws":7,"losses":40,"wins":1},"gpt-6-luna":{"draws":2,"losses":1,"wins":3},"gpt-6-sol":{"draws":2,"losses":8,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":14,"losses":2,"wins":12},"inclusionai/ling-3.0-flash":{"draws":11,"losses":5,"wins":8},"meituan/longcat-2.0":{"draws":20,"losses":10,"wins":24},"meta/muse-glimmer-30b":{"draws":11,"losses":2,"wins":19},"meta/muse-spark-1.2":{"draws":11,"losses":7,"wins":26},"meta/muse-spark-1.3":{"draws":12,"losses":10,"wins":12},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":5},"mistralai/mistral-medium-3-5":{"draws":7,"losses":4,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":15,"losses":25,"wins":30},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":6},"o3":{"draws":6,"losses":27,"wins":39},"openai/gpt-oss-120b":{"draws":14,"losses":2,"wins":16},"poolside/laguna-s-2.1":{"draws":19,"losses":4,"wins":29},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":7},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":19,"wins":14},"qwen/qwen3.8-27b":{"draws":6,"losses":11,"wins":9},"qwen/qwen3.8-flash":{"draws":12,"losses":9,"wins":11},"qwen/qwen3.8-max":{"draws":13,"losses":13,"wins":15},"qwen/qwen3.8-max-0902":{"draws":4,"losses":6,"wins":4},"stealth/ox-alpha":{"draws":37,"losses":60,"wins":50},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":16},"tencent/hy3-preview":{"draws":1,"losses":4,"wins":7},"tencent/hy4-preview":{"draws":8,"losses":16,"wins":12},"thinkingmachines/inkling":{"draws":17,"losses":4,"wins":27},"thinkingmachines/inkling-small":{"draws":18,"losses":3,"wins":19},"x-ai/grok-4.5":{"draws":14,"losses":28,"wins":22},"x-ai/grok-4.6":{"draws":11,"losses":23,"wins":12},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":5,"losses":0,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":7,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":2,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":13,"losses":22,"wins":27},"z-ai/glm-5.3":{"draws":10,"losses":26,"wins":12},"z-ai/glm-5.3-flash":{"draws":6,"losses":19,"wins":23},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":4}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":5,"wins":12},"claude-fable-5":{"draws":7,"losses":26,"wins":17},"claude-fable-5-1":{"draws":2,"losses":61,"wins":5},"claude-opus-4-5":{"draws":7,"losses":10,"wins":29},"claude-opus-4-8":{"draws":2,"losses":4,"wins":10},"claude-opus-5":{"draws":8,"losses":31,"wins":7},"claude-opus-5-5":{"draws":2,"losses":11,"wins":1},"claude-sonnet-5":{"draws":12,"losses":13,"wins":21},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":8,"losses":6,"wins":28},"deepseek/deepseek-v4-pro":{"draws":4,"losses":11,"wins":27},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":10,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":0,"wins":1},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":4,"losses":10,"wins":40},"google/gemini-3.5-flash-lite":{"draws":7,"losses":14,"wins":41},"google/gemini-3.6-flash":{"draws":7,"losses":25,"wins":34},"google/gemini-3.8-flash":{"draws":9,"losses":17,"wins":32},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":6},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":3,"wins":14},"gpt-5.4":{"draws":5,"losses":18,"wins":21},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":3},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":8},"gpt-5.5":{"draws":0,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":7,"wins":16},"gpt-5.6-sol":{"draws":13,"losses":26,"wins":19},"gpt-5.6-terra":{"draws":14,"losses":15,"wins":25},"gpt-6-astra":{"draws":7,"losses":48,"wins":5},"gpt-6-luna":{"draws":3,"losses":1,"wins":6},"gpt-6-sol":{"draws":1,"losses":4,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":3,"wins":10},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":8},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":26},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":12},"meta/muse-spark-1.2":{"draws":5,"losses":9,"wins":20},"meta/muse-spark-1.3":{"draws":7,"losses":8,"wins":13},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":7},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":6,"losses":17,"wins":33},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":10},"o3":{"draws":0,"losses":9,"wins":49},"openai/gpt-oss-120b":{"draws":4,"losses":5,"wins":21},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":16},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":18,"wins":18},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":17},"qwen/qwen3.8-flash":{"draws":9,"losses":6,"wins":19},"qwen/qwen3.8-max":{"draws":3,"losses":12,"wins":27},"qwen/qwen3.8-max-0902":{"draws":3,"losses":1,"wins":4},"stealth/ox-alpha":{"draws":32,"losses":52,"wins":78},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":20},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":13},"tencent/hy4-preview":{"draws":4,"losses":13,"wins":19},"thinkingmachines/inkling":{"draws":5,"losses":4,"wins":17},"thinkingmachines/inkling-small":{"draws":8,"losses":2,"wins":26},"x-ai/grok-4.5":{"draws":1,"losses":16,"wins":21},"x-ai/grok-4.6":{"draws":5,"losses":25,"wins":22},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":5,"losses":0,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":11,"losses":15,"wins":18},"z-ai/glm-5.3":{"draws":5,"losses":32,"wins":17},"z-ai/glm-5.3-flash":{"draws":7,"losses":21,"wins":22},"z-ai/glm-5.3-flashx":{"draws":0,"losses":2,"wins":0}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":7,"wins":5},"claude-fable-5":{"draws":2,"losses":6,"wins":0},"claude-fable-5-1":{"draws":1,"losses":13,"wins":0},"claude-opus-4-5":{"draws":15,"losses":20,"wins":3},"claude-opus-4-8":{"draws":15,"losses":17,"wins":2},"claude-opus-5":{"draws":3,"losses":31,"wins":4},"claude-opus-5-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":3,"losses":8,"wins":3},"cohere/north-mini-code":{"draws":8,"losses":7,"wins":15},"deepseek/deepseek-v4-flash":{"draws":24,"losses":23,"wins":19},"deepseek/deepseek-v4-pro":{"draws":3,"losses":3,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":12,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":14,"losses":30,"wins":20},"google/gemini-3.5-flash":{"draws":10,"losses":8,"wins":2},"google/gemini-3.5-flash-lite":{"draws":14,"losses":19,"wins":7},"google/gemini-3.6-flash":{"draws":9,"losses":23,"wins":2},"google/gemini-3.8-flash":{"draws":8,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":12,"losses":8,"wins":10},"gpt-4.1":{"draws":8,"losses":9,"wins":1},"gpt-5":{"draws":19,"losses":17,"wins":6},"gpt-5.4":{"draws":3,"losses":5,"wins":0},"gpt-5.4-mini":{"draws":12,"losses":26,"wins":10},"gpt-5.4-nano":{"draws":18,"losses":33,"wins":9},"gpt-5.5":{"draws":11,"losses":18,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":5,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":8,"wins":0},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"gpt-6-luna":{"draws":2,"losses":3,"wins":1},"gpt-6-sol":{"draws":0,"losses":10,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":23,"losses":11,"wins":14},"meituan/longcat-2.0":{"draws":11,"losses":20,"wins":11},"meta/muse-glimmer-30b":{"draws":2,"losses":5,"wins":5},"meta/muse-spark-1.2":{"draws":3,"losses":10,"wins":1},"meta/muse-spark-1.3":{"draws":2,"losses":5,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":11,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":7,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":7,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":24,"losses":15,"wins":11},"o3":{"draws":10,"losses":18,"wins":4},"openai/gpt-oss-120b":{"draws":6,"losses":7,"wins":1},"poolside/laguna-s-2.1":{"draws":20,"losses":17,"wins":7},"qwen/qwen3.7-max":{"draws":14,"losses":19,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":14,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":10,"wins":0},"qwen/qwen3.8-27b":{"draws":3,"losses":5,"wins":0},"qwen/qwen3.8-flash":{"draws":7,"losses":5,"wins":2},"qwen/qwen3.8-max":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":3},"stealth/ox-alpha":{"draws":15,"losses":18,"wins":3},"stepfun/step-3.7-flash":{"draws":13,"losses":7,"wins":4},"tencent/hy3-preview":{"draws":21,"losses":14,"wins":1},"tencent/hy4-preview":{"draws":3,"losses":8,"wins":1},"thinkingmachines/inkling":{"draws":8,"losses":20,"wins":10},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":5,"losses":22,"wins":1},"x-ai/grok-4.6":{"draws":3,"losses":3,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":13,"losses":13,"wins":2},"xiaomi/mimo-v2.5":{"draws":49,"losses":40,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":11,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":5,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":25,"losses":28,"wins":5},"z-ai/glm-5.3":{"draws":1,"losses":3,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":4,"wins":1},"z-ai/glm-5.3-flashx":{"draws":1,"losses":11,"wins":0}},"moonshotai/kimi-k2.7-code":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":7},"claude-fable-5":{"draws":4,"losses":0,"wins":2},"claude-fable-5-1":{"draws":2,"losses":10,"wins":0},"claude-opus-4-5":{"draws":13,"losses":30,"wins":21},"claude-opus-4-8":{"draws":10,"losses":15,"wins":9},"claude-opus-5":{"draws":10,"losses":66,"wins":2},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":2,"losses":4,"wins":4},"cohere/north-mini-code":{"draws":5,"losses":6,"wins":11},"deepseek/deepseek-v4-flash":{"draws":12,"losses":10,"wins":14},"deepseek/deepseek-v4-pro":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":6,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":7,"wins":5},"google/gemini-3.1-flash-lite":{"draws":12,"losses":3,"wins":23},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":5},"google/gemini-3.5-flash-lite":{"draws":8,"losses":11,"wins":5},"google/gemini-3.6-flash":{"draws":6,"losses":20,"wins":4},"google/gemini-3.8-flash":{"draws":3,"losses":4,"wins":1},"google/gemma-4-31b-it":{"draws":6,"losses":2,"wins":22},"gpt-4.1":{"draws":8,"losses":5,"wins":7},"gpt-5":{"draws":10,"losses":10,"wins":10},"gpt-5.4":{"draws":1,"losses":9,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":15},"gpt-5.4-nano":{"draws":6,"losses":16,"wins":14},"gpt-5.5":{"draws":20,"losses":9,"wins":11},"gpt-5.6-luna":{"draws":6,"losses":3,"wins":5},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":4},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":2,"losses":0,"wins":0},"gpt-6-sol":{"draws":3,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":14},"meta/muse-glimmer-30b":{"draws":2,"losses":3,"wins":9},"meta/muse-spark-1.2":{"draws":5,"losses":4,"wins":5},"meta/muse-spark-1.3":{"draws":4,"losses":0,"wins":0},"minimax/minimax-m3":{"draws":10,"losses":3,"wins":15},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":2,"losses":3,"wins":7},"nex-agi/nex-n2-pro":{"draws":6,"losses":0,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":4,"wins":18},"o3":{"draws":2,"losses":9,"wins":13},"openai/gpt-oss-120b":{"draws":2,"losses":5,"wins":3},"poolside/laguna-s-2.1":{"draws":12,"losses":17,"wins":3},"qwen/qwen3.7-max":{"draws":8,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":15,"losses":2,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":5,"wins":1},"qwen/qwen3.8-max":{"draws":2,"losses":6,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":4},"stealth/ox-alpha":{"draws":5,"losses":10,"wins":11},"stepfun/step-3.7-flash":{"draws":9,"losses":5,"wins":8},"tencent/hy3-preview":{"draws":7,"losses":7,"wins":6},"tencent/hy4-preview":{"draws":2,"losses":6,"wins":2},"thinkingmachines/inkling":{"draws":6,"losses":13,"wins":15},"thinkingmachines/inkling-small":{"draws":2,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":1},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":2,"wins":15},"xiaomi/mimo-v2.5":{"draws":33,"losses":13,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":0,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":20,"wins":19},"z-ai/glm-5.3":{"draws":2,"losses":2,"wins":2},"z-ai/glm-5.3-flashx":{"draws":7,"losses":1,"wins":6}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":13,"wins":21},"claude-fable-5":{"draws":14,"losses":30,"wins":0},"claude-fable-5-1":{"draws":7,"losses":38,"wins":1},"claude-opus-4-5":{"draws":39,"losses":38,"wins":27},"claude-opus-4-8":{"draws":2,"losses":4,"wins":8},"claude-opus-5":{"draws":7,"losses":39,"wins":4},"claude-opus-5-5":{"draws":0,"losses":2,"wins":4},"claude-sonnet-5":{"draws":37,"losses":27,"wins":38},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":21,"losses":12,"wins":15},"deepseek/deepseek-v4-pro":{"draws":20,"losses":13,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":16,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":4},"google/gemini-3.5-flash":{"draws":25,"losses":22,"wins":13},"google/gemini-3.5-flash-lite":{"draws":84,"losses":50,"wins":100},"google/gemini-3.6-flash":{"draws":74,"losses":87,"wins":57},"google/gemini-3.8-flash":{"draws":29,"losses":28,"wins":7},"google/gemma-4-31b-it":{"draws":0,"losses":4,"wins":12},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":12,"losses":11,"wins":1},"gpt-5.4":{"draws":32,"losses":62,"wins":8},"gpt-5.4-mini":{"draws":7,"losses":8,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":9,"wins":15},"gpt-5.5":{"draws":13,"losses":4,"wins":7},"gpt-5.6-luna":{"draws":41,"losses":26,"wins":37},"gpt-5.6-sol":{"draws":17,"losses":59,"wins":18},"gpt-5.6-terra":{"draws":20,"losses":13,"wins":13},"gpt-6-astra":{"draws":2,"losses":38,"wins":4},"gpt-6-luna":{"draws":0,"losses":0,"wins":2},"gpt-6-sol":{"draws":3,"losses":9,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":20,"losses":2,"wins":18},"inclusionai/ling-3.0-flash":{"draws":13,"losses":9,"wins":24},"meituan/longcat-2.0":{"draws":28,"losses":8,"wins":48},"meta/muse-glimmer-30b":{"draws":21,"losses":9,"wins":8},"meta/muse-spark-1.2":{"draws":19,"losses":23,"wins":28},"meta/muse-spark-1.3":{"draws":10,"losses":28,"wins":12},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":14,"losses":3,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":28,"losses":32,"wins":14},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":3},"o3":{"draws":21,"losses":59,"wins":50},"openai/gpt-oss-120b":{"draws":19,"losses":6,"wins":19},"poolside/laguna-s-2.1":{"draws":36,"losses":4,"wins":36},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":4},"qwen/qwen3.7-plus":{"draws":5,"losses":4,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":25,"wins":15},"qwen/qwen3.8-27b":{"draws":14,"losses":6,"wins":8},"qwen/qwen3.8-flash":{"draws":15,"losses":3,"wins":14},"qwen/qwen3.8-max":{"draws":18,"losses":13,"wins":11},"qwen/qwen3.8-max-0902":{"draws":4,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":50,"losses":69,"wins":48},"stepfun/step-3.7-flash":{"draws":15,"losses":3,"wins":22},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":16,"losses":14,"wins":16},"thinkingmachines/inkling":{"draws":37,"losses":6,"wins":41},"thinkingmachines/inkling-small":{"draws":28,"losses":4,"wins":19},"x-ai/grok-4.5":{"draws":27,"losses":45,"wins":20},"x-ai/grok-4.6":{"draws":26,"losses":15,"wins":11},"x-ai/grok-4.7":{"draws":2,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":10,"losses":3,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":10,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":1},"z-ai/glm-5.2":{"draws":24,"losses":21,"wins":21},"z-ai/glm-5.3":{"draws":9,"losses":36,"wins":9},"z-ai/glm-5.3-flash":{"draws":24,"losses":10,"wins":20},"z-ai/glm-5.3-flashx":{"draws":6,"losses":4,"wins":2}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":10,"wins":2},"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-fable-5-1":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":2,"losses":29,"wins":1},"claude-opus-4-8":{"draws":7,"losses":19,"wins":0},"claude-opus-5":{"draws":0,"losses":22,"wins":0},"claude-opus-5-5":{"draws":2,"losses":2,"wins":0},"claude-sonnet-5":{"draws":3,"losses":9,"wins":0},"cohere/north-mini-code":{"draws":9,"losses":9,"wins":6},"deepseek/deepseek-v4-flash":{"draws":1,"losses":16,"wins":17},"deepseek/deepseek-v4-pro":{"draws":0,"losses":8,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":7,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":14,"wins":16},"google/gemini-3.5-flash":{"draws":3,"losses":7,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":7,"wins":5},"google/gemini-3.6-flash":{"draws":0,"losses":18,"wins":2},"google/gemini-3.8-flash":{"draws":1,"losses":6,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":9,"wins":9},"gpt-4.1":{"draws":0,"losses":6,"wins":0},"gpt-5":{"draws":2,"losses":24,"wins":6},"gpt-5.4":{"draws":2,"losses":7,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":8,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":26,"wins":14},"gpt-5.5":{"draws":1,"losses":34,"wins":3},"gpt-5.6-luna":{"draws":3,"losses":9,"wins":2},"gpt-5.6-sol":{"draws":1,"losses":9,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":0,"losses":6,"wins":0},"gpt-6-sol":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":1,"losses":3,"wins":2},"inclusionai/ling-3.0-flash":{"draws":5,"losses":14,"wins":11},"meituan/longcat-2.0":{"draws":3,"losses":27,"wins":12},"meta/muse-glimmer-30b":{"draws":2,"losses":6,"wins":0},"meta/muse-spark-1.2":{"draws":1,"losses":7,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":1,"losses":17,"wins":8},"mistralai/mistral-medium-3-5":{"draws":1,"losses":3,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":0,"losses":10,"wins":0},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":20,"wins":10},"o3":{"draws":1,"losses":27,"wins":0},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":1},"poolside/laguna-s-2.1":{"draws":8,"losses":14,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":14,"wins":2},"qwen/qwen3.7-plus":{"draws":4,"losses":14,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":10,"wins":2},"qwen/qwen3.8-27b":{"draws":0,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":4,"losses":9,"wins":1},"qwen/qwen3.8-max":{"draws":0,"losses":10,"wins":0},"qwen/qwen3.8-max-0902":{"draws":0,"losses":3,"wins":1},"stealth/ox-alpha":{"draws":4,"losses":25,"wins":5},"stepfun/step-3.7-flash":{"draws":2,"losses":7,"wins":11},"tencent/hy3-preview":{"draws":0,"losses":5,"wins":1},"tencent/hy4-preview":{"draws":0,"losses":8,"wins":0},"thinkingmachines/inkling":{"draws":0,"losses":11,"wins":11},"thinkingmachines/inkling-small":{"draws":1,"losses":7,"wins":6},"x-ai/grok-4.5":{"draws":5,"losses":19,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":7,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":9,"wins":4},"xiaomi/mimo-v2.5":{"draws":0,"losses":31,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":17,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":15,"losses":18,"wins":1},"z-ai/glm-5.3":{"draws":0,"losses":9,"wins":1},"z-ai/glm-5.3-flash":{"draws":2,"losses":7,"wins":3},"z-ai/glm-5.3-flashx":{"draws":0,"losses":2,"wins":0}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":5,"wins":3},"claude-fable-5":{"draws":4,"losses":8,"wins":0},"claude-fable-5-1":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":16,"losses":10,"wins":12},"claude-opus-4-8":{"draws":6,"losses":18,"wins":0},"claude-opus-5":{"draws":2,"losses":34,"wins":0},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":4,"losses":6,"wins":4},"cohere/north-mini-code":{"draws":6,"losses":4,"wins":6},"deepseek/deepseek-v4-flash":{"draws":12,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":5,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":14},"google/gemini-3.5-flash":{"draws":4,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":8,"losses":8,"wins":8},"google/gemini-3.6-flash":{"draws":5,"losses":13,"wins":2},"google/gemini-3.8-flash":{"draws":4,"losses":4,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":8,"wins":2},"gpt-4.1":{"draws":2,"losses":5,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":11,"losses":13,"wins":8},"gpt-5.4":{"draws":0,"losses":6,"wins":2},"gpt-5.4-mini":{"draws":19,"losses":5,"wins":8},"gpt-5.4-nano":{"draws":19,"losses":14,"wins":19},"gpt-5.5":{"draws":12,"losses":19,"wins":5},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":1,"losses":4,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":7,"wins":2},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"gpt-6-luna":{"draws":4,"losses":2,"wins":2},"gpt-6-sol":{"draws":2,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":13,"losses":12,"wins":7},"meituan/longcat-2.0":{"draws":7,"losses":5,"wins":10},"meta/muse-glimmer-30b":{"draws":2,"losses":2,"wins":0},"meta/muse-spark-1.2":{"draws":4,"losses":2,"wins":2},"meta/muse-spark-1.3":{"draws":3,"losses":6,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":8,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":3,"wins":3},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":4,"wins":8},"o3":{"draws":7,"losses":11,"wins":2},"openai/gpt-oss-120b":{"draws":1,"losses":5,"wins":2},"poolside/laguna-s-2.1":{"draws":17,"losses":7,"wins":2},"qwen/qwen3.7-max":{"draws":8,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":8,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":5,"wins":1},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.8-max":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":8,"wins":0},"stealth/ox-alpha":{"draws":2,"losses":9,"wins":1},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":6},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":1,"wins":1},"thinkingmachines/inkling":{"draws":10,"losses":8,"wins":2},"thinkingmachines/inkling-small":{"draws":3,"losses":5,"wins":4},"x-ai/grok-4.5":{"draws":8,"losses":14,"wins":2},"x-ai/grok-4.6":{"draws":3,"losses":5,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":15,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":29,"losses":20,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":10,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":2},"z-ai/glm-5.2":{"draws":25,"losses":6,"wins":5},"z-ai/glm-5.3":{"draws":3,"losses":5,"wins":6},"z-ai/glm-5.3-flash":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flashx":{"draws":2,"losses":6,"wins":2}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":3,"wins":2},"claude-fable-5":{"draws":4,"losses":9,"wins":1},"claude-fable-5-1":{"draws":0,"losses":5,"wins":1},"claude-opus-4-5":{"draws":19,"losses":32,"wins":17},"claude-opus-4-8":{"draws":9,"losses":17,"wins":12},"claude-opus-5":{"draws":2,"losses":38,"wins":4},"claude-opus-5-5":{"draws":1,"losses":1,"wins":2},"claude-sonnet-5":{"draws":2,"losses":7,"wins":5},"cohere/north-mini-code":{"draws":13,"losses":4,"wins":11},"deepseek/deepseek-v4-flash":{"draws":9,"losses":7,"wins":10},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":5,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":18},"google/gemini-3.5-flash":{"draws":6,"losses":11,"wins":11},"google/gemini-3.5-flash-lite":{"draws":8,"losses":4,"wins":30},"google/gemini-3.6-flash":{"draws":13,"losses":18,"wins":17},"google/gemini-3.8-flash":{"draws":1,"losses":5,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":16},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":16,"losses":12,"wins":8},"gpt-5.4":{"draws":5,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":16,"wins":9},"gpt-5.4-nano":{"draws":4,"losses":20,"wins":22},"gpt-5.5":{"draws":16,"losses":13,"wins":5},"gpt-5.6-sol":{"draws":4,"losses":8,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":4,"wins":0},"gpt-6-astra":{"draws":0,"losses":14,"wins":0},"gpt-6-luna":{"draws":4,"losses":4,"wins":2},"gpt-6-sol":{"draws":2,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":15},"meituan/longcat-2.0":{"draws":14,"losses":10,"wins":20},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":1},"meta/muse-spark-1.2":{"draws":0,"losses":12,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":12,"wins":2},"minimax/minimax-m3":{"draws":9,"losses":1,"wins":12},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":10,"wins":4},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":6,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":7,"wins":5},"o3":{"draws":3,"losses":5,"wins":10},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":5,"losses":1,"wins":16},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":11},"qwen/qwen3.7-plus":{"draws":4,"losses":8,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.8-27b":{"draws":3,"losses":5,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":5},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":4},"stealth/ox-alpha":{"draws":13,"losses":25,"wins":10},"stepfun/step-3.7-flash":{"draws":11,"losses":3,"wins":10},"tencent/hy3-preview":{"draws":14,"losses":3,"wins":5},"tencent/hy4-preview":{"draws":3,"losses":6,"wins":1},"thinkingmachines/inkling":{"draws":8,"losses":9,"wins":9},"thinkingmachines/inkling-small":{"draws":11,"losses":2,"wins":7},"x-ai/grok-4.5":{"draws":6,"losses":7,"wins":11},"x-ai/grok-4.6":{"draws":7,"losses":11,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":7,"losses":0,"wins":13},"xiaomi/mimo-v2.5":{"draws":26,"losses":4,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":14,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":8,"losses":27,"wins":17},"z-ai/glm-5.3":{"draws":0,"losses":14,"wins":0},"z-ai/glm-5.3-flash":{"draws":8,"losses":1,"wins":7},"z-ai/glm-5.3-flashx":{"draws":0,"losses":11,"wins":3}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":15,"wins":18},"claude-fable-5":{"draws":9,"losses":25,"wins":2},"claude-fable-5-1":{"draws":5,"losses":16,"wins":1},"claude-opus-4-5":{"draws":9,"losses":31,"wins":0},"claude-opus-4-8":{"draws":4,"losses":6,"wins":0},"claude-opus-5":{"draws":6,"losses":22,"wins":0},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":23,"losses":23,"wins":8},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":2},"deepseek/deepseek-v4-flash":{"draws":28,"losses":18,"wins":14},"deepseek/deepseek-v4-pro":{"draws":14,"losses":24,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":13,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":12,"wins":3},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":16,"losses":19,"wins":7},"google/gemini-3.5-flash-lite":{"draws":30,"losses":38,"wins":28},"google/gemini-3.6-flash":{"draws":25,"losses":27,"wins":12},"google/gemini-3.8-flash":{"draws":10,"losses":23,"wins":1},"google/gemma-4-31b-it":{"draws":4,"losses":2,"wins":4},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":6,"losses":5,"wins":1},"gpt-5.4":{"draws":23,"losses":19,"wins":2},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":8},"gpt-5.5":{"draws":6,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":27,"losses":21,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":26,"wins":2},"gpt-5.6-terra":{"draws":20,"losses":26,"wins":2},"gpt-6-astra":{"draws":0,"losses":22,"wins":0},"gpt-6-luna":{"draws":5,"losses":5,"wins":4},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":18,"losses":8,"wins":14},"inclusionai/ling-3.0-flash":{"draws":6,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":15,"losses":16,"wins":11},"meta/muse-glimmer-30b":{"draws":23,"losses":15,"wins":14},"meta/muse-spark-1.2":{"draws":12,"losses":13,"wins":3},"meta/muse-spark-1.3":{"draws":15,"losses":24,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":1},"mistralai/mistral-medium-3-5":{"draws":16,"losses":7,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":32,"wins":3},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":2,"wins":3},"o3":{"draws":8,"losses":26,"wins":10},"openai/gpt-oss-120b":{"draws":12,"losses":11,"wins":5},"poolside/laguna-s-2.1":{"draws":12,"losses":10,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":1,"losses":2,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":24,"wins":3},"qwen/qwen3.8-27b":{"draws":8,"losses":11,"wins":7},"qwen/qwen3.8-flash":{"draws":14,"losses":8,"wins":6},"qwen/qwen3.8-max":{"draws":24,"losses":23,"wins":3},"qwen/qwen3.8-max-0902":{"draws":4,"losses":5,"wins":1},"stealth/ox-alpha":{"draws":46,"losses":78,"wins":16},"stepfun/step-3.7-flash":{"draws":2,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":4,"losses":4,"wins":0},"tencent/hy4-preview":{"draws":15,"losses":15,"wins":8},"thinkingmachines/inkling":{"draws":16,"losses":8,"wins":10},"thinkingmachines/inkling-small":{"draws":25,"losses":15,"wins":16},"x-ai/grok-4.5":{"draws":13,"losses":17,"wins":0},"x-ai/grok-4.6":{"draws":14,"losses":20,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":9,"losses":6,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":6,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":2,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":26,"losses":24,"wins":12},"z-ai/glm-5.3":{"draws":12,"losses":17,"wins":3},"z-ai/glm-5.3-flash":{"draws":6,"losses":27,"wins":5},"z-ai/glm-5.3-flashx":{"draws":5,"losses":5,"wins":0}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":22,"wins":17},"claude-fable-5":{"draws":18,"losses":29,"wins":5},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-opus-4-5":{"draws":58,"losses":66,"wins":6},"claude-opus-4-8":{"draws":13,"losses":11,"wins":2},"claude-opus-5":{"draws":8,"losses":60,"wins":6},"claude-opus-5-5":{"draws":0,"losses":16,"wins":0},"claude-sonnet-5":{"draws":47,"losses":69,"wins":10},"cohere/north-mini-code":{"draws":10,"losses":6,"wins":0},"deepseek/deepseek-v4-flash":{"draws":45,"losses":27,"wins":12},"deepseek/deepseek-v4-pro":{"draws":28,"losses":23,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":17,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":5,"wins":15},"google/gemini-3.5-flash":{"draws":33,"losses":32,"wins":11},"google/gemini-3.5-flash-lite":{"draws":167,"losses":88,"wins":95},"google/gemini-3.6-flash":{"draws":134,"losses":121,"wins":29},"google/gemini-3.8-flash":{"draws":20,"losses":34,"wins":2},"google/gemma-4-31b-it":{"draws":2,"losses":10,"wins":2},"gpt-4.1":{"draws":6,"losses":1,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":10,"losses":9,"wins":7},"gpt-5.4":{"draws":48,"losses":52,"wins":8},"gpt-5.4-mini":{"draws":18,"losses":13,"wins":7},"gpt-5.4-nano":{"draws":17,"losses":12,"wins":11},"gpt-5.5":{"draws":11,"losses":11,"wins":6},"gpt-5.6-luna":{"draws":60,"losses":46,"wins":30},"gpt-5.6-sol":{"draws":27,"losses":112,"wins":1},"gpt-5.6-terra":{"draws":28,"losses":26,"wins":4},"gpt-6-astra":{"draws":11,"losses":37,"wins":0},"gpt-6-luna":{"draws":8,"losses":3,"wins":1},"gpt-6-sol":{"draws":5,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":2,"wins":2},"inception/mercury-2.5-preview":{"draws":26,"losses":11,"wins":15},"inclusionai/ling-3.0-flash":{"draws":42,"losses":8,"wins":20},"meituan/longcat-2.0":{"draws":57,"losses":51,"wins":40},"meta/muse-glimmer-30b":{"draws":40,"losses":12,"wins":20},"meta/muse-spark-1.2":{"draws":29,"losses":52,"wins":11},"meta/muse-spark-1.3":{"draws":24,"losses":24,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":7,"wins":9},"mistralai/mistral-medium-3-5":{"draws":26,"losses":10,"wins":16},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":66,"losses":78,"wins":2},"nex-agi/nex-n2-pro":{"draws":7,"losses":3,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":5,"wins":3},"o3":{"draws":50,"losses":63,"wins":45},"openai/gpt-oss-120b":{"draws":37,"losses":17,"wins":12},"poolside/laguna-s-2.1":{"draws":45,"losses":27,"wins":20},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":5},"qwen/qwen3.7-plus":{"draws":14,"losses":3,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":26,"wins":6},"qwen/qwen3.8-27b":{"draws":9,"losses":21,"wins":10},"qwen/qwen3.8-flash":{"draws":23,"losses":14,"wins":7},"qwen/qwen3.8-max":{"draws":31,"losses":16,"wins":13},"qwen/qwen3.8-max-0902":{"draws":4,"losses":0,"wins":2},"stealth/ox-alpha":{"draws":71,"losses":93,"wins":24},"stepfun/step-3.7-flash":{"draws":20,"losses":17,"wins":9},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":29,"losses":24,"wins":9},"thinkingmachines/inkling":{"draws":60,"losses":36,"wins":52},"thinkingmachines/inkling-small":{"draws":46,"losses":13,"wins":28},"x-ai/grok-4.5":{"draws":51,"losses":66,"wins":17},"x-ai/grok-4.6":{"draws":23,"losses":26,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":16,"losses":7,"wins":5},"xiaomi/mimo-v2.5":{"draws":21,"losses":9,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":8,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":3,"wins":0},"z-ai/glm-5.2":{"draws":60,"losses":25,"wins":17},"z-ai/glm-5.3":{"draws":23,"losses":27,"wins":4},"z-ai/glm-5.3-flash":{"draws":36,"losses":26,"wins":10},"z-ai/glm-5.3-flashx":{"draws":6,"losses":6,"wins":2}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":3,"wins":10},"claude-fable-5":{"draws":2,"losses":4,"wins":2},"claude-fable-5-1":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":34,"losses":29,"wins":19},"claude-opus-4-8":{"draws":18,"losses":20,"wins":14},"claude-opus-5":{"draws":5,"losses":48,"wins":17},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":0,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":12,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":12,"losses":6,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":4,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":0,"wins":5},"google/gemini-3.1-flash-lite":{"draws":17,"losses":5,"wins":10},"google/gemini-3.5-flash":{"draws":15,"losses":8,"wins":9},"google/gemini-3.5-flash-lite":{"draws":16,"losses":13,"wins":11},"google/gemini-3.6-flash":{"draws":6,"losses":18,"wins":10},"google/gemini-3.8-flash":{"draws":0,"losses":8,"wins":6},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":13},"gpt-4.1":{"draws":12,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":16,"losses":18,"wins":12},"gpt-5.4":{"draws":1,"losses":5,"wins":6},"gpt-5.4-mini":{"draws":11,"losses":6,"wins":13},"gpt-5.4-nano":{"draws":14,"losses":16,"wins":26},"gpt-5.5":{"draws":19,"losses":22,"wins":13},"gpt-5.6-luna":{"draws":3,"losses":4,"wins":3},"gpt-5.6-sol":{"draws":5,"losses":3,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":12,"wins":4},"gpt-6-astra":{"draws":2,"losses":13,"wins":1},"gpt-6-luna":{"draws":2,"losses":6,"wins":2},"gpt-6-sol":{"draws":3,"losses":3,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":3},"inclusionai/ling-3.0-flash":{"draws":18,"losses":3,"wins":13},"meituan/longcat-2.0":{"draws":16,"losses":3,"wins":26},"meta/muse-glimmer-30b":{"draws":6,"losses":4,"wins":6},"meta/muse-spark-1.2":{"draws":0,"losses":9,"wins":1},"meta/muse-spark-1.3":{"draws":5,"losses":4,"wins":5},"minimax/minimax-m3":{"draws":14,"losses":10,"wins":14},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":4,"wins":4},"moonshotai/kimi-k3":{"draws":7,"losses":4,"wins":5},"nex-agi/nex-n2-pro":{"draws":6,"losses":3,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":9,"wins":10},"o3":{"draws":11,"losses":11,"wins":10},"openai/gpt-oss-120b":{"draws":4,"losses":6,"wins":4},"poolside/laguna-s-2.1":{"draws":14,"losses":2,"wins":16},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":6},"qwen/qwen3.7-plus":{"draws":10,"losses":6,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":4,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":13,"wins":1},"qwen/qwen3.8-flash":{"draws":9,"losses":6,"wins":3},"qwen/qwen3.8-max":{"draws":9,"losses":7,"wins":4},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":1},"stealth/ox-alpha":{"draws":8,"losses":22,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":3,"wins":13},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":4,"losses":8,"wins":4},"thinkingmachines/inkling":{"draws":18,"losses":8,"wins":20},"thinkingmachines/inkling-small":{"draws":3,"losses":5,"wins":6},"x-ai/grok-4.5":{"draws":14,"losses":13,"wins":7},"x-ai/grok-4.6":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.7":{"draws":1,"losses":7,"wins":2},"x-ai/grok-build-0.1":{"draws":16,"losses":6,"wins":10},"xiaomi/mimo-v2.5":{"draws":31,"losses":13,"wins":32},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":10,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":23,"losses":27,"wins":18},"z-ai/glm-5.3":{"draws":6,"losses":5,"wins":5},"z-ai/glm-5.3-flash":{"draws":2,"losses":2,"wins":4},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":2}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":4,"losses":5,"wins":1},"claude-fable-5-1":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":10,"losses":15,"wins":13},"claude-opus-4-8":{"draws":7,"losses":25,"wins":10},"claude-opus-5":{"draws":11,"losses":25,"wins":0},"claude-opus-5-5":{"draws":1,"losses":7,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":10,"losses":9,"wins":17},"deepseek/deepseek-v4-flash":{"draws":14,"losses":12,"wins":10},"deepseek/deepseek-v4-pro":{"draws":6,"losses":6,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":6,"wins":4},"google/gemini-3.1-flash-lite":{"draws":10,"losses":2,"wins":14},"google/gemini-3.5-flash":{"draws":6,"losses":7,"wins":3},"google/gemini-3.5-flash-lite":{"draws":12,"losses":2,"wins":8},"google/gemini-3.6-flash":{"draws":6,"losses":24,"wins":8},"google/gemini-3.8-flash":{"draws":2,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":9},"gpt-4.1":{"draws":6,"losses":6,"wins":2},"gpt-5":{"draws":12,"losses":9,"wins":9},"gpt-5.4":{"draws":2,"losses":2,"wins":4},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":15},"gpt-5.4-nano":{"draws":12,"losses":17,"wins":29},"gpt-5.5":{"draws":20,"losses":14,"wins":8},"gpt-5.6-luna":{"draws":0,"losses":1,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":6,"wins":2},"gpt-5.6-terra":{"draws":4,"losses":3,"wins":3},"gpt-6-astra":{"draws":0,"losses":8,"wins":0},"gpt-6-luna":{"draws":0,"losses":2,"wins":2},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":1,"wins":9},"inclusionai/ling-3.0-flash":{"draws":14,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":11,"losses":8,"wins":17},"meta/muse-glimmer-30b":{"draws":7,"losses":7,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":14,"wins":6},"meta/muse-spark-1.3":{"draws":0,"losses":3,"wins":3},"minimax/minimax-m3":{"draws":6,"losses":9,"wins":15},"mistralai/mistral-medium-3-5":{"draws":4,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":9,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":7,"wins":4},"nex-agi/nex-n2-pro":{"draws":8,"losses":5,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":12,"wins":12},"o3":{"draws":4,"losses":13,"wins":15},"openai/gpt-oss-120b":{"draws":5,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":22,"losses":10,"wins":4},"qwen/qwen3.7-max":{"draws":14,"losses":12,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":6,"wins":3},"qwen/qwen3.8-27b":{"draws":1,"losses":9,"wins":4},"qwen/qwen3.8-flash":{"draws":6,"losses":4,"wins":4},"qwen/qwen3.8-max":{"draws":5,"losses":2,"wins":9},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":9,"losses":20,"wins":5},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":16},"tencent/hy3-preview":{"draws":14,"losses":2,"wins":8},"tencent/hy4-preview":{"draws":4,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":8,"losses":2,"wins":14},"thinkingmachines/inkling-small":{"draws":4,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":20,"wins":8},"x-ai/grok-4.6":{"draws":3,"losses":1,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":31,"losses":3,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":8,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":22,"losses":27,"wins":11},"z-ai/glm-5.3":{"draws":0,"losses":5,"wins":1},"z-ai/glm-5.3-flash":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.3-flashx":{"draws":2,"losses":0,"wins":0}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":15,"wins":14},"claude-fable-5":{"draws":14,"losses":27,"wins":7},"claude-fable-5-1":{"draws":7,"losses":38,"wins":1},"claude-opus-4-5":{"draws":29,"losses":17,"wins":4},"claude-opus-4-8":{"draws":10,"losses":2,"wins":6},"claude-opus-5":{"draws":5,"losses":23,"wins":6},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":25,"losses":22,"wins":11},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":25,"losses":18,"wins":15},"deepseek/deepseek-v4-pro":{"draws":18,"losses":21,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":24,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":17,"losses":26,"wins":17},"google/gemini-3.5-flash-lite":{"draws":29,"losses":18,"wins":37},"google/gemini-3.6-flash":{"draws":25,"losses":39,"wins":20},"google/gemini-3.8-flash":{"draws":14,"losses":26,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":4,"losses":1,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":5,"wins":3},"gpt-5.4":{"draws":17,"losses":27,"wins":10},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":4,"wins":8},"gpt-5.5":{"draws":7,"losses":6,"wins":1},"gpt-5.6-luna":{"draws":29,"losses":8,"wins":15},"gpt-5.6-sol":{"draws":13,"losses":33,"wins":6},"gpt-5.6-terra":{"draws":26,"losses":13,"wins":13},"gpt-6-astra":{"draws":4,"losses":31,"wins":1},"gpt-6-luna":{"draws":2,"losses":1,"wins":1},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":1,"wins":6},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":20},"inclusionai/ling-3.0-flash":{"draws":12,"losses":2,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":19},"meta/muse-glimmer-30b":{"draws":25,"losses":2,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":10},"meta/muse-spark-1.3":{"draws":17,"losses":25,"wins":4},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":17,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":26,"wins":9},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":3},"o3":{"draws":9,"losses":25,"wins":22},"openai/gpt-oss-120b":{"draws":24,"losses":4,"wins":18},"poolside/laguna-s-2.1":{"draws":16,"losses":3,"wins":11},"qwen/qwen3.7-max":{"draws":5,"losses":3,"wins":2},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":16,"wins":5},"qwen/qwen3.8-27b":{"draws":14,"losses":7,"wins":7},"qwen/qwen3.8-flash":{"draws":14,"losses":8,"wins":6},"qwen/qwen3.8-max":{"draws":27,"losses":12,"wins":15},"qwen/qwen3.8-max-0902":{"draws":5,"losses":3,"wins":0},"stealth/ox-alpha":{"draws":60,"losses":70,"wins":37},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":4},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":18,"losses":21,"wins":17},"thinkingmachines/inkling":{"draws":22,"losses":4,"wins":12},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":23},"x-ai/grok-4.5":{"draws":12,"losses":20,"wins":6},"x-ai/grok-4.6":{"draws":15,"losses":24,"wins":9},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":14,"losses":4,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":29,"losses":20,"wins":15},"z-ai/glm-5.3":{"draws":13,"losses":32,"wins":7},"z-ai/glm-5.3-flash":{"draws":15,"losses":21,"wins":8},"z-ai/glm-5.3-flashx":{"draws":0,"losses":6,"wins":2}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":14,"wins":15},"claude-fable-5":{"draws":2,"losses":17,"wins":3},"claude-fable-5-1":{"draws":0,"losses":22,"wins":0},"claude-opus-4-5":{"draws":6,"losses":17,"wins":5},"claude-opus-4-8":{"draws":5,"losses":8,"wins":3},"claude-opus-5":{"draws":1,"losses":4,"wins":1},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":9,"losses":12,"wins":9},"cohere/north-mini-code":{"draws":0,"losses":3,"wins":7},"deepseek/deepseek-v4-flash":{"draws":7,"losses":16,"wins":19},"deepseek/deepseek-v4-pro":{"draws":3,"losses":14,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":14,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":5,"losses":14,"wins":13},"google/gemini-3.5-flash-lite":{"draws":6,"losses":24,"wins":32},"google/gemini-3.6-flash":{"draws":12,"losses":37,"wins":9},"google/gemini-3.8-flash":{"draws":4,"losses":23,"wins":7},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":1},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":0,"losses":4,"wins":2},"gpt-5.4":{"draws":1,"losses":18,"wins":5},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":3,"wins":11},"gpt-5.5":{"draws":1,"losses":5,"wins":6},"gpt-5.6-luna":{"draws":5,"losses":11,"wins":16},"gpt-5.6-sol":{"draws":2,"losses":19,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":13,"wins":6},"gpt-6-astra":{"draws":0,"losses":28,"wins":2},"gpt-6-luna":{"draws":0,"losses":4,"wins":0},"gpt-6-sol":{"draws":0,"losses":2,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":4,"losses":3,"wins":17},"inclusionai/ling-3.0-flash":{"draws":3,"losses":3,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":6,"wins":11},"meta/muse-glimmer-30b":{"draws":8,"losses":9,"wins":17},"meta/muse-spark-1.2":{"draws":6,"losses":15,"wins":9},"meta/muse-spark-1.3":{"draws":7,"losses":18,"wins":5},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":5,"wins":13},"moonshotai/kimi-k3":{"draws":6,"losses":7,"wins":9},"nex-agi/nex-n2-pro":{"draws":0,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":0},"o3":{"draws":6,"losses":20,"wins":24},"openai/gpt-oss-120b":{"draws":2,"losses":12,"wins":16},"poolside/laguna-s-2.1":{"draws":2,"losses":16,"wins":12},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":12},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":12,"wins":13},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":4,"losses":8,"wins":8},"qwen/qwen3.8-max":{"draws":5,"losses":9,"wins":16},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":19,"losses":67,"wins":27},"stepfun/step-3.7-flash":{"draws":0,"losses":5,"wins":13},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":6,"losses":20,"wins":2},"thinkingmachines/inkling":{"draws":8,"losses":6,"wins":20},"thinkingmachines/inkling-small":{"draws":6,"losses":11,"wins":19},"x-ai/grok-4.5":{"draws":3,"losses":8,"wins":19},"x-ai/grok-4.6":{"draws":7,"losses":10,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":0,"losses":3,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":11},"z-ai/glm-5.2":{"draws":13,"losses":20,"wins":17},"z-ai/glm-5.3":{"draws":2,"losses":14,"wins":6},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":7},"z-ai/glm-5.3-flashx":{"draws":0,"losses":2,"wins":0}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":4,"wins":19},"claude-fable-5":{"draws":19,"losses":20,"wins":13},"claude-fable-5-1":{"draws":1,"losses":51,"wins":4},"claude-opus-4-5":{"draws":15,"losses":10,"wins":25},"claude-opus-4-8":{"draws":8,"losses":3,"wins":7},"claude-opus-5":{"draws":6,"losses":24,"wins":2},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":10,"losses":11,"wins":19},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":9},"deepseek/deepseek-v4-flash":{"draws":22,"losses":3,"wins":23},"deepseek/deepseek-v4-pro":{"draws":11,"losses":8,"wins":25},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":5,"wins":20},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":26,"losses":13,"wins":19},"google/gemini-3.5-flash-lite":{"draws":30,"losses":6,"wins":30},"google/gemini-3.6-flash":{"draws":28,"losses":24,"wins":32},"google/gemini-3.8-flash":{"draws":13,"losses":13,"wins":20},"google/gemma-4-31b-it":{"draws":8,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":8},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":6,"losses":5,"wins":1},"gpt-5.4":{"draws":11,"losses":17,"wins":14},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":8,"losses":0,"wins":4},"gpt-5.5":{"draws":4,"losses":9,"wins":5},"gpt-5.6-luna":{"draws":21,"losses":8,"wins":23},"gpt-5.6-sol":{"draws":17,"losses":27,"wins":16},"gpt-5.6-terra":{"draws":17,"losses":8,"wins":21},"gpt-6-astra":{"draws":8,"losses":40,"wins":2},"gpt-6-luna":{"draws":0,"losses":3,"wins":5},"gpt-6-sol":{"draws":2,"losses":3,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":15,"losses":0,"wins":15},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":14},"meituan/longcat-2.0":{"draws":13,"losses":4,"wins":11},"meta/muse-glimmer-30b":{"draws":9,"losses":11,"wins":8},"meta/muse-spark-1.2":{"draws":12,"losses":8,"wins":20},"meta/muse-spark-1.3":{"draws":15,"losses":15,"wins":16},"minimax/minimax-m3":{"draws":7,"losses":1,"wins":8},"mistralai/mistral-medium-3-5":{"draws":8,"losses":2,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":5},"moonshotai/kimi-k3":{"draws":20,"losses":6,"wins":16},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":1,"wins":6},"o3":{"draws":12,"losses":13,"wins":25},"openai/gpt-oss-120b":{"draws":13,"losses":4,"wins":11},"poolside/laguna-s-2.1":{"draws":17,"losses":0,"wins":9},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":16,"wins":26},"qwen/qwen3.8-27b":{"draws":11,"losses":6,"wins":11},"qwen/qwen3.8-flash":{"draws":7,"losses":0,"wins":5},"qwen/qwen3.8-max":{"draws":17,"losses":11,"wins":22},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":8},"stealth/ox-alpha":{"draws":47,"losses":37,"wins":57},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":5},"tencent/hy4-preview":{"draws":16,"losses":13,"wins":23},"thinkingmachines/inkling":{"draws":13,"losses":5,"wins":12},"thinkingmachines/inkling-small":{"draws":20,"losses":1,"wins":15},"x-ai/grok-4.5":{"draws":7,"losses":19,"wins":8},"x-ai/grok-4.6":{"draws":16,"losses":17,"wins":13},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":7,"losses":0,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":3,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":19,"losses":7,"wins":28},"z-ai/glm-5.3":{"draws":13,"losses":29,"wins":10},"z-ai/glm-5.3-flash":{"draws":13,"losses":11,"wins":28},"z-ai/glm-5.3-flashx":{"draws":3,"losses":8,"wins":7}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":18,"losses":11,"wins":17},"claude-fable-5":{"draws":3,"losses":36,"wins":13},"claude-fable-5-1":{"draws":4,"losses":48,"wins":0},"claude-opus-4-5":{"draws":15,"losses":14,"wins":36},"claude-opus-4-8":{"draws":10,"losses":9,"wins":5},"claude-opus-5":{"draws":6,"losses":15,"wins":3},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":14,"losses":11,"wins":21},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":13,"losses":9,"wins":24},"deepseek/deepseek-v4-pro":{"draws":9,"losses":9,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":12,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":6,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":18,"losses":26,"wins":10},"google/gemini-3.5-flash-lite":{"draws":29,"losses":18,"wins":29},"google/gemini-3.6-flash":{"draws":29,"losses":33,"wins":29},"google/gemini-3.8-flash":{"draws":14,"losses":16,"wins":14},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":1,"wins":2},"gpt-5.4":{"draws":13,"losses":22,"wins":11},"gpt-5.4-mini":{"draws":5,"losses":3,"wins":6},"gpt-5.4-nano":{"draws":4,"losses":2,"wins":8},"gpt-5.5":{"draws":2,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":19,"losses":8,"wins":17},"gpt-5.6-sol":{"draws":12,"losses":30,"wins":14},"gpt-5.6-terra":{"draws":22,"losses":16,"wins":16},"gpt-6-astra":{"draws":10,"losses":42,"wins":2},"gpt-6-luna":{"draws":4,"losses":1,"wins":3},"gpt-6-sol":{"draws":4,"losses":5,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":14,"losses":5,"wins":9},"inclusionai/ling-3.0-flash":{"draws":13,"losses":3,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":7,"wins":14},"meta/muse-glimmer-30b":{"draws":10,"losses":11,"wins":15},"meta/muse-spark-1.2":{"draws":10,"losses":11,"wins":15},"meta/muse-spark-1.3":{"draws":11,"losses":27,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":3},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":15,"losses":14,"wins":11},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":2,"wins":7},"o3":{"draws":8,"losses":17,"wins":38},"openai/gpt-oss-120b":{"draws":16,"losses":4,"wins":14},"poolside/laguna-s-2.1":{"draws":11,"losses":6,"wins":6},"qwen/qwen3.7-max":{"draws":5,"losses":1,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":6,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":11,"wins":23},"qwen/qwen3.8-27b":{"draws":8,"losses":10,"wins":6},"qwen/qwen3.8-flash":{"draws":14,"losses":16,"wins":6},"qwen/qwen3.8-max":{"draws":20,"losses":15,"wins":24},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":42,"losses":64,"wins":56},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":13,"losses":24,"wins":13},"thinkingmachines/inkling":{"draws":7,"losses":11,"wins":16},"thinkingmachines/inkling-small":{"draws":30,"losses":31,"wins":42},"x-ai/grok-4.5":{"draws":9,"losses":23,"wins":10},"x-ai/grok-4.6":{"draws":15,"losses":26,"wins":15},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":14,"losses":3,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":3,"wins":5},"z-ai/glm-5.2":{"draws":18,"losses":13,"wins":17},"z-ai/glm-5.3":{"draws":13,"losses":17,"wins":8},"z-ai/glm-5.3-flash":{"draws":15,"losses":20,"wins":11},"z-ai/glm-5.3-flashx":{"draws":7,"losses":1,"wins":0}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":0,"wins":7},"claude-fable-5":{"draws":3,"losses":7,"wins":2},"claude-fable-5-1":{"draws":0,"losses":13,"wins":1},"claude-opus-4-5":{"draws":3,"losses":2,"wins":3},"claude-opus-4-8":{"draws":5,"losses":1,"wins":2},"claude-opus-5":{"draws":3,"losses":11,"wins":2},"claude-opus-5-5":{"draws":2,"losses":15,"wins":1},"claude-sonnet-5":{"draws":2,"losses":0,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":4,"wins":10},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":9,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":5,"losses":2,"wins":1},"google/gemini-3.5-flash-lite":{"draws":4,"losses":2,"wins":4},"google/gemini-3.6-flash":{"draws":4,"losses":8,"wins":0},"google/gemini-3.8-flash":{"draws":2,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":5,"wins":5},"gpt-5.4":{"draws":6,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":2},"gpt-5.5":{"draws":5,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":5,"losses":1,"wins":2},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":5,"losses":12,"wins":3},"gpt-6-sol":{"draws":2,"losses":9,"wins":5},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":12},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":3},"meta/muse-spark-1.2":{"draws":3,"losses":3,"wins":4},"meta/muse-spark-1.3":{"draws":5,"losses":5,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":1},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":2,"losses":0,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":2,"wins":7},"o3":{"draws":2,"losses":3,"wins":3},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":6},"poolside/laguna-s-2.1":{"draws":2,"losses":6,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":4,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":4,"wins":5},"qwen/qwen3.8-max-0902":{"draws":6,"losses":14,"wins":6},"stealth/ox-alpha":{"draws":8,"losses":21,"wins":11},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":6,"losses":5,"wins":3},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling-small":{"draws":4,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":1,"losses":2,"wins":1},"x-ai/grok-4.6":{"draws":4,"losses":2,"wins":0},"x-ai/grok-4.7":{"draws":3,"losses":7,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":13,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":6,"wins":5},"z-ai/glm-5.2":{"draws":2,"losses":3,"wins":7},"z-ai/glm-5.3":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":5,"wins":4},"z-ai/glm-5.3-flashx":{"draws":10,"losses":11,"wins":7}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":37,"wins":64},"claude-fable-5":{"draws":42,"losses":76,"wins":32},"claude-fable-5-1":{"draws":18,"losses":167,"wins":5},"claude-opus-4-5":{"draws":48,"losses":48,"wins":52},"claude-opus-4-8":{"draws":12,"losses":13,"wins":21},"claude-opus-5":{"draws":13,"losses":60,"wins":19},"claude-opus-5-5":{"draws":5,"losses":31,"wins":2},"claude-sonnet-5":{"draws":44,"losses":52,"wins":72},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":10},"deepseek/deepseek-v4-flash":{"draws":50,"losses":46,"wins":72},"deepseek/deepseek-v4-pro":{"draws":38,"losses":53,"wins":47},"deepseek/deepseek-v4-pro-0813":{"draws":36,"losses":55,"wins":53},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":6,"wins":13},"google/gemini-3.1-flash-lite":{"draws":7,"losses":7,"wins":12},"google/gemini-3.5-flash":{"draws":41,"losses":48,"wins":63},"google/gemini-3.5-flash-lite":{"draws":61,"losses":59,"wins":132},"google/gemini-3.6-flash":{"draws":63,"losses":104,"wins":83},"google/gemini-3.8-flash":{"draws":35,"losses":78,"wins":45},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":15},"gpt-4.1":{"draws":3,"losses":0,"wins":9},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":14,"losses":17,"wins":27},"gpt-5.4":{"draws":46,"losses":60,"wins":50},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":9,"losses":6,"wins":23},"gpt-5.5":{"draws":11,"losses":11,"wins":18},"gpt-5.6-luna":{"draws":40,"losses":32,"wins":54},"gpt-5.6-sol":{"draws":21,"losses":108,"wins":35},"gpt-5.6-terra":{"draws":48,"losses":36,"wins":58},"gpt-6-astra":{"draws":20,"losses":137,"wins":7},"gpt-6-luna":{"draws":4,"losses":10,"wins":6},"gpt-6-sol":{"draws":5,"losses":24,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":12,"losses":2,"wins":10},"inception/mercury-2.5-preview":{"draws":37,"losses":19,"wins":46},"inclusionai/ling-3.0-flash":{"draws":7,"losses":10,"wins":27},"meituan/longcat-2.0":{"draws":22,"losses":13,"wins":59},"meta/muse-glimmer-30b":{"draws":34,"losses":25,"wins":75},"meta/muse-spark-1.2":{"draws":29,"losses":44,"wins":59},"meta/muse-spark-1.3":{"draws":35,"losses":51,"wins":50},"minimax/minimax-m3":{"draws":7,"losses":5,"wins":14},"mistralai/mistral-medium-3-5":{"draws":21,"losses":20,"wins":45},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":6,"wins":5},"moonshotai/kimi-k3":{"draws":33,"losses":67,"wins":52},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":0,"wins":24},"o3":{"draws":12,"losses":67,"wins":65},"openai/gpt-oss-120b":{"draws":26,"losses":24,"wins":64},"poolside/laguna-s-2.1":{"draws":24,"losses":16,"wins":46},"qwen/qwen3.7-max":{"draws":3,"losses":5,"wins":10},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":52,"losses":63,"wins":47},"qwen/qwen3.8-27b":{"draws":17,"losses":39,"wins":30},"qwen/qwen3.8-flash":{"draws":23,"losses":31,"wins":32},"qwen/qwen3.8-max":{"draws":51,"losses":48,"wins":47},"qwen/qwen3.8-max-0902":{"draws":7,"losses":9,"wins":8},"stealth/ox-alpha":{"draws":129,"losses":272,"wins":199},"stepfun/step-3.7-flash":{"draws":3,"losses":10,"wins":23},"tencent/hy3-preview":{"draws":16,"losses":3,"wins":9},"tencent/hy4-preview":{"draws":30,"losses":77,"wins":45},"thinkingmachines/inkling":{"draws":16,"losses":24,"wins":68},"thinkingmachines/inkling-small":{"draws":56,"losses":35,"wins":65},"x-ai/grok-4.5":{"draws":22,"losses":54,"wins":28},"x-ai/grok-4.6":{"draws":44,"losses":66,"wins":56},"x-ai/grok-4.7":{"draws":4,"losses":12,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":18,"losses":9,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":13,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":8,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":8,"wins":2},"z-ai/glm-5.2":{"draws":45,"losses":49,"wins":90},"z-ai/glm-5.3":{"draws":40,"losses":80,"wins":30},"z-ai/glm-5.3-flash":{"draws":36,"losses":68,"wins":58},"z-ai/glm-5.3-flashx":{"draws":5,"losses":13,"wins":14}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":1,"wins":1},"claude-fable-5":{"draws":0,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":2,"wins":0},"claude-opus-4-5":{"draws":25,"losses":14,"wins":3},"claude-opus-4-8":{"draws":14,"losses":9,"wins":7},"claude-opus-5":{"draws":11,"losses":32,"wins":1},"claude-opus-5-5":{"draws":2,"losses":6,"wins":0},"claude-sonnet-5":{"draws":1,"losses":5,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":12,"losses":1,"wins":5},"deepseek/deepseek-v4-pro":{"draws":2,"losses":6,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":4,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":7,"losses":3,"wins":8},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":1},"google/gemini-3.5-flash-lite":{"draws":8,"losses":1,"wins":13},"google/gemini-3.6-flash":{"draws":9,"losses":13,"wins":2},"google/gemini-3.8-flash":{"draws":3,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":16},"gpt-4.1":{"draws":6,"losses":2,"wins":0},"gpt-5":{"draws":11,"losses":4,"wins":1},"gpt-5.4":{"draws":2,"losses":0,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":5,"wins":2},"gpt-5.4-nano":{"draws":18,"losses":18,"wins":2},"gpt-5.5":{"draws":5,"losses":11,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":5,"wins":3},"gpt-6-astra":{"draws":0,"losses":8,"wins":0},"gpt-6-luna":{"draws":3,"losses":1,"wins":0},"gpt-6-sol":{"draws":1,"losses":5,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":4},"meituan/longcat-2.0":{"draws":5,"losses":7,"wins":14},"meta/muse-glimmer-30b":{"draws":8,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":2,"losses":4,"wins":2},"meta/muse-spark-1.3":{"draws":5,"losses":8,"wins":5},"minimax/minimax-m3":{"draws":8,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":4,"wins":1},"moonshotai/kimi-k3":{"draws":6,"losses":10,"wins":0},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":8,"wins":2},"o3":{"draws":6,"losses":10,"wins":6},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":10,"losses":10,"wins":6},"qwen/qwen3.7-max":{"draws":10,"losses":5,"wins":7},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.8-max":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":5,"losses":20,"wins":1},"stepfun/step-3.7-flash":{"draws":0,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":0,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":7,"wins":3},"thinkingmachines/inkling-small":{"draws":5,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":12,"wins":1},"x-ai/grok-4.6":{"draws":6,"losses":5,"wins":3},"x-ai/grok-4.7":{"draws":1,"losses":1,"wins":0},"x-ai/grok-build-0.1":{"draws":12,"losses":8,"wins":0},"xiaomi/mimo-v2.5":{"draws":38,"losses":13,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":8,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":12,"losses":15,"wins":3},"z-ai/glm-5.3":{"draws":7,"losses":7,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":3,"wins":0},"z-ai/glm-5.3-flashx":{"draws":2,"losses":0,"wins":0}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":25},"claude-fable-5":{"draws":3,"losses":32,"wins":13},"claude-fable-5-1":{"draws":0,"losses":32,"wins":4},"claude-opus-4-5":{"draws":6,"losses":5,"wins":23},"claude-opus-4-8":{"draws":2,"losses":8,"wins":4},"claude-opus-5":{"draws":0,"losses":12,"wins":6},"claude-opus-5-5":{"draws":0,"losses":0,"wins":2},"claude-sonnet-5":{"draws":10,"losses":12,"wins":24},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":11,"losses":11,"wins":30},"deepseek/deepseek-v4-pro":{"draws":8,"losses":13,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":19,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":6,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":13,"wins":21},"google/gemini-3.5-flash-lite":{"draws":13,"losses":19,"wins":50},"google/gemini-3.6-flash":{"draws":10,"losses":46,"wins":34},"google/gemini-3.8-flash":{"draws":4,"losses":11,"wins":15},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":4,"wins":3},"gpt-5.4":{"draws":4,"losses":17,"wins":23},"gpt-5.4-mini":{"draws":4,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":3,"wins":7},"gpt-5.5":{"draws":4,"losses":1,"wins":7},"gpt-5.6-luna":{"draws":7,"losses":9,"wins":24},"gpt-5.6-sol":{"draws":9,"losses":13,"wins":20},"gpt-5.6-terra":{"draws":9,"losses":13,"wins":16},"gpt-6-astra":{"draws":2,"losses":34,"wins":4},"gpt-6-luna":{"draws":0,"losses":2,"wins":6},"gpt-6-sol":{"draws":0,"losses":4,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":9,"losses":3,"wins":22},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":8},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":20},"meta/muse-glimmer-30b":{"draws":7,"losses":5,"wins":20},"meta/muse-spark-1.2":{"draws":4,"losses":5,"wins":15},"meta/muse-spark-1.3":{"draws":5,"losses":12,"wins":21},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":7,"losses":2,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":6,"losses":20,"wins":10},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":1,"wins":7},"o3":{"draws":4,"losses":9,"wins":35},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":19},"poolside/laguna-s-2.1":{"draws":5,"losses":5,"wins":14},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":13,"wins":16},"qwen/qwen3.8-27b":{"draws":6,"losses":4,"wins":12},"qwen/qwen3.8-flash":{"draws":2,"losses":9,"wins":13},"qwen/qwen3.8-max":{"draws":8,"losses":18,"wins":16},"qwen/qwen3.8-max-0902":{"draws":0,"losses":3,"wins":5},"stealth/ox-alpha":{"draws":27,"losses":46,"wins":66},"stepfun/step-3.7-flash":{"draws":0,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":4,"losses":8,"wins":10},"thinkingmachines/inkling":{"draws":11,"losses":2,"wins":23},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":30},"x-ai/grok-4.5":{"draws":10,"losses":9,"wins":15},"x-ai/grok-4.6":{"draws":9,"losses":22,"wins":13},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":5},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":12,"losses":15,"wins":25},"z-ai/glm-5.3":{"draws":6,"losses":28,"wins":8},"z-ai/glm-5.3-flash":{"draws":0,"losses":14,"wins":14},"z-ai/glm-5.3-flashx":{"draws":0,"losses":5,"wins":5}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":19,"wins":9},"claude-fable-5":{"draws":4,"losses":13,"wins":1},"claude-fable-5-1":{"draws":2,"losses":22,"wins":0},"claude-opus-4-5":{"draws":18,"losses":33,"wins":7},"claude-opus-4-8":{"draws":5,"losses":8,"wins":3},"claude-opus-5":{"draws":2,"losses":27,"wins":3},"claude-opus-5-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":26,"losses":32,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":8,"wins":0},"deepseek/deepseek-v4-flash":{"draws":12,"losses":15,"wins":15},"deepseek/deepseek-v4-pro":{"draws":9,"losses":9,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":10,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":6,"wins":10},"google/gemini-3.5-flash":{"draws":9,"losses":12,"wins":9},"google/gemini-3.5-flash-lite":{"draws":61,"losses":55,"wins":28},"google/gemini-3.6-flash":{"draws":65,"losses":59,"wins":22},"google/gemini-3.8-flash":{"draws":11,"losses":16,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":4},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":1,"losses":8,"wins":3},"gpt-5.4":{"draws":14,"losses":33,"wins":11},"gpt-5.4-mini":{"draws":3,"losses":5,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":16,"wins":9},"gpt-5.5":{"draws":7,"losses":11,"wins":4},"gpt-5.6-luna":{"draws":20,"losses":32,"wins":16},"gpt-5.6-sol":{"draws":4,"losses":46,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":15,"wins":5},"gpt-6-astra":{"draws":2,"losses":18,"wins":0},"gpt-6-luna":{"draws":5,"losses":1,"wins":0},"gpt-6-sol":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":14,"losses":1,"wins":9},"inclusionai/ling-3.0-flash":{"draws":6,"losses":11,"wins":9},"meituan/longcat-2.0":{"draws":16,"losses":21,"wins":21},"meta/muse-glimmer-30b":{"draws":21,"losses":10,"wins":5},"meta/muse-spark-1.2":{"draws":13,"losses":28,"wins":9},"meta/muse-spark-1.3":{"draws":9,"losses":9,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":5,"wins":9},"mistralai/mistral-medium-3-5":{"draws":10,"losses":1,"wins":7},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":8,"wins":0},"moonshotai/kimi-k3":{"draws":26,"losses":35,"wins":9},"nex-agi/nex-n2-pro":{"draws":0,"losses":8,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":10,"wins":5},"o3":{"draws":24,"losses":40,"wins":11},"openai/gpt-oss-120b":{"draws":18,"losses":11,"wins":3},"poolside/laguna-s-2.1":{"draws":24,"losses":17,"wins":11},"qwen/qwen3.7-max":{"draws":3,"losses":6,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":5,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":10,"wins":3},"qwen/qwen3.8-27b":{"draws":10,"losses":8,"wins":4},"qwen/qwen3.8-flash":{"draws":10,"losses":5,"wins":5},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":5},"qwen/qwen3.8-max-0902":{"draws":6,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":17,"losses":62,"wins":18},"stepfun/step-3.7-flash":{"draws":6,"losses":11,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":14,"losses":13,"wins":3},"thinkingmachines/inkling":{"draws":12,"losses":14,"wins":16},"thinkingmachines/inkling-small":{"draws":16,"losses":6,"wins":8},"x-ai/grok-4.5":{"draws":15,"losses":21,"wins":6},"x-ai/grok-4.6":{"draws":7,"losses":13,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":20,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":8,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":10,"wins":11},"z-ai/glm-5.3":{"draws":7,"losses":19,"wins":2},"z-ai/glm-5.3-flash":{"draws":10,"losses":14,"wins":4},"z-ai/glm-5.3-flashx":{"draws":5,"losses":7,"wins":0}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":16,"wins":10},"claude-fable-5":{"draws":16,"losses":18,"wins":4},"claude-fable-5-1":{"draws":2,"losses":38,"wins":0},"claude-opus-4-5":{"draws":17,"losses":29,"wins":7},"claude-opus-4-8":{"draws":0,"losses":6,"wins":2},"claude-opus-5":{"draws":1,"losses":7,"wins":2},"claude-opus-5-5":{"draws":1,"losses":7,"wins":0},"claude-sonnet-5":{"draws":17,"losses":26,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":31,"losses":20,"wins":7},"deepseek/deepseek-v4-pro":{"draws":16,"losses":30,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":25,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":2},"google/gemini-3.5-flash":{"draws":13,"losses":16,"wins":11},"google/gemini-3.5-flash-lite":{"draws":41,"losses":43,"wins":17},"google/gemini-3.6-flash":{"draws":24,"losses":37,"wins":19},"google/gemini-3.8-flash":{"draws":18,"losses":16,"wins":10},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":3},"gpt-4.1":{"draws":1,"losses":2,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":3,"losses":4,"wins":1},"gpt-5.4":{"draws":22,"losses":11,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":0},"gpt-5.4-nano":{"draws":4,"losses":5,"wins":5},"gpt-5.5":{"draws":5,"losses":10,"wins":3},"gpt-5.6-luna":{"draws":19,"losses":17,"wins":22},"gpt-5.6-sol":{"draws":3,"losses":23,"wins":10},"gpt-5.6-terra":{"draws":18,"losses":17,"wins":11},"gpt-6-astra":{"draws":4,"losses":32,"wins":0},"gpt-6-luna":{"draws":0,"losses":4,"wins":0},"gpt-6-sol":{"draws":1,"losses":1,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":18,"losses":12,"wins":14},"inclusionai/ling-3.0-flash":{"draws":9,"losses":3,"wins":6},"meituan/longcat-2.0":{"draws":6,"losses":17,"wins":11},"meta/muse-glimmer-30b":{"draws":24,"losses":23,"wins":9},"meta/muse-spark-1.2":{"draws":7,"losses":24,"wins":11},"meta/muse-spark-1.3":{"draws":10,"losses":20,"wins":6},"mistralai/mistral-medium-3-5":{"draws":15,"losses":9,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":21,"losses":22,"wins":6},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":0},"o3":{"draws":14,"losses":25,"wins":15},"openai/gpt-oss-120b":{"draws":19,"losses":15,"wins":8},"poolside/laguna-s-2.1":{"draws":21,"losses":18,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":35,"wins":6},"qwen/qwen3.8-27b":{"draws":5,"losses":24,"wins":5},"qwen/qwen3.8-flash":{"draws":14,"losses":11,"wins":3},"qwen/qwen3.8-max":{"draws":35,"losses":53,"wins":17},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":55,"losses":76,"wins":23},"stepfun/step-3.7-flash":{"draws":6,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":1},"tencent/hy4-preview":{"draws":15,"losses":22,"wins":7},"thinkingmachines/inkling":{"draws":9,"losses":19,"wins":4},"thinkingmachines/inkling-small":{"draws":26,"losses":25,"wins":19},"x-ai/grok-4.5":{"draws":9,"losses":22,"wins":9},"x-ai/grok-4.6":{"draws":15,"losses":22,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":1},"xiaomi/mimo-v2.5":{"draws":12,"losses":3,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":28,"losses":29,"wins":21},"z-ai/glm-5.3":{"draws":6,"losses":20,"wins":6},"z-ai/glm-5.3-flash":{"draws":14,"losses":27,"wins":9},"z-ai/glm-5.3-flashx":{"draws":1,"losses":2,"wins":1}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":1,"wins":6},"claude-fable-5":{"draws":2,"losses":6,"wins":6},"claude-fable-5-1":{"draws":0,"losses":9,"wins":1},"claude-opus-4-5":{"draws":25,"losses":17,"wins":26},"claude-opus-4-8":{"draws":11,"losses":18,"wins":25},"claude-opus-5":{"draws":15,"losses":64,"wins":21},"claude-opus-5-5":{"draws":2,"losses":16,"wins":0},"claude-sonnet-5":{"draws":1,"losses":1,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":18},"deepseek/deepseek-v4-flash":{"draws":7,"losses":3,"wins":26},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":8,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":0,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":1,"wins":19},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":15},"google/gemini-3.5-flash-lite":{"draws":8,"losses":11,"wins":39},"google/gemini-3.6-flash":{"draws":19,"losses":33,"wins":30},"google/gemini-3.8-flash":{"draws":5,"losses":4,"wins":19},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":6},"gpt-4.1":{"draws":6,"losses":4,"wins":6},"gpt-5":{"draws":8,"losses":6,"wins":22},"gpt-5.4":{"draws":9,"losses":6,"wins":7},"gpt-5.4-mini":{"draws":11,"losses":2,"wins":17},"gpt-5.4-nano":{"draws":4,"losses":17,"wins":25},"gpt-5.5":{"draws":20,"losses":15,"wins":23},"gpt-5.6-luna":{"draws":4,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":16,"wins":12},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":11},"gpt-6-astra":{"draws":3,"losses":15,"wins":0},"gpt-6-luna":{"draws":2,"losses":0,"wins":2},"gpt-6-sol":{"draws":0,"losses":1,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":13,"losses":1,"wins":32},"meituan/longcat-2.0":{"draws":5,"losses":14,"wins":39},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":5},"meta/muse-spark-1.2":{"draws":1,"losses":4,"wins":11},"meta/muse-spark-1.3":{"draws":4,"losses":8,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":23},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":9},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":1,"wins":12},"moonshotai/kimi-k3":{"draws":12,"losses":12,"wins":14},"nex-agi/nex-n2-pro":{"draws":8,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":24},"o3":{"draws":4,"losses":9,"wins":15},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":12,"losses":9,"wins":33},"qwen/qwen3.7-max":{"draws":14,"losses":4,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":8,"wins":11},"qwen/qwen3.8-27b":{"draws":3,"losses":7,"wins":8},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":4},"qwen/qwen3.8-max":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.8-max-0902":{"draws":3,"losses":3,"wins":2},"stealth/ox-alpha":{"draws":9,"losses":17,"wins":24},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":18},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":5},"tencent/hy4-preview":{"draws":6,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":10,"losses":8,"wins":20},"thinkingmachines/inkling-small":{"draws":2,"losses":6,"wins":0},"x-ai/grok-4.5":{"draws":10,"losses":8,"wins":10},"x-ai/grok-4.6":{"draws":6,"losses":2,"wins":6},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":1},"x-ai/grok-build-0.1":{"draws":12,"losses":0,"wins":14},"xiaomi/mimo-v2.5":{"draws":31,"losses":11,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":10,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":4},"z-ai/glm-5.2":{"draws":14,"losses":22,"wins":30},"z-ai/glm-5.3":{"draws":4,"losses":7,"wins":3},"z-ai/glm-5.3-flash":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.3-flashx":{"draws":2,"losses":3,"wins":5}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":21},"claude-fable-5":{"draws":8,"losses":22,"wins":26},"claude-fable-5-1":{"draws":5,"losses":50,"wins":9},"claude-opus-4-5":{"draws":15,"losses":3,"wins":34},"claude-opus-4-8":{"draws":0,"losses":1,"wins":9},"claude-opus-5":{"draws":4,"losses":18,"wins":8},"claude-opus-5-5":{"draws":0,"losses":6,"wins":2},"claude-sonnet-5":{"draws":10,"losses":10,"wins":28},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":10,"losses":3,"wins":43},"deepseek/deepseek-v4-pro":{"draws":9,"losses":5,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":4,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":1,"wins":8},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":7,"losses":7,"wins":30},"google/gemini-3.5-flash-lite":{"draws":6,"losses":5,"wins":45},"google/gemini-3.6-flash":{"draws":15,"losses":16,"wins":37},"google/gemini-3.8-flash":{"draws":13,"losses":15,"wins":26},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":5,"losses":0,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":1,"wins":2},"gpt-5.4":{"draws":12,"losses":16,"wins":20},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":9},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":9},"gpt-5.5":{"draws":0,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":5,"losses":4,"wins":19},"gpt-5.6-sol":{"draws":11,"losses":21,"wins":24},"gpt-5.6-terra":{"draws":12,"losses":9,"wins":27},"gpt-6-astra":{"draws":2,"losses":52,"wins":8},"gpt-6-luna":{"draws":2,"losses":0,"wins":6},"gpt-6-sol":{"draws":2,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":6,"losses":1,"wins":13},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":5},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":8},"meta/muse-glimmer-30b":{"draws":4,"losses":0,"wins":14},"meta/muse-spark-1.2":{"draws":6,"losses":2,"wins":24},"meta/muse-spark-1.3":{"draws":10,"losses":15,"wins":21},"minimax/minimax-m3":{"draws":3,"losses":0,"wins":5},"mistralai/mistral-medium-3-5":{"draws":6,"losses":0,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":19,"losses":8,"wins":21},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":4},"o3":{"draws":6,"losses":2,"wins":28},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":13},"poolside/laguna-s-2.1":{"draws":3,"losses":0,"wins":7},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":10,"wins":24},"qwen/qwen3.8-27b":{"draws":4,"losses":6,"wins":16},"qwen/qwen3.8-flash":{"draws":10,"losses":6,"wins":12},"qwen/qwen3.8-max":{"draws":10,"losses":7,"wins":29},"qwen/qwen3.8-max-0902":{"draws":0,"losses":3,"wins":7},"stealth/ox-alpha":{"draws":33,"losses":38,"wins":103},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":6},"tencent/hy4-preview":{"draws":7,"losses":10,"wins":25},"thinkingmachines/inkling":{"draws":5,"losses":0,"wins":15},"thinkingmachines/inkling-small":{"draws":4,"losses":1,"wins":23},"x-ai/grok-4.5":{"draws":6,"losses":6,"wins":14},"x-ai/grok-4.6":{"draws":10,"losses":12,"wins":14},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":1},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":11,"losses":0,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":1,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":6,"wins":21},"z-ai/glm-5.3":{"draws":11,"losses":22,"wins":25},"z-ai/glm-5.3-flash":{"draws":12,"losses":12,"wins":22},"z-ai/glm-5.3-flashx":{"draws":2,"losses":0,"wins":6}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":2},"claude-fable-5":{"draws":0,"losses":3,"wins":3},"claude-fable-5-1":{"draws":0,"losses":5,"wins":1},"claude-opus-4-5":{"draws":0,"losses":1,"wins":9},"claude-opus-4-8":{"draws":0,"losses":3,"wins":3},"claude-opus-5":{"draws":1,"losses":4,"wins":5},"claude-opus-5-5":{"draws":1,"losses":20,"wins":5},"claude-sonnet-5":{"draws":0,"losses":1,"wins":7},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":12},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":0,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":12},"google/gemini-3.5-flash-lite":{"draws":1,"losses":0,"wins":13},"google/gemini-3.6-flash":{"draws":0,"losses":0,"wins":12},"google/gemini-3.8-flash":{"draws":1,"losses":0,"wins":9},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":4},"gpt-5.4":{"draws":0,"losses":2,"wins":4},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":8},"gpt-5.5":{"draws":0,"losses":2,"wins":6},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":5,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":10},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"gpt-6-luna":{"draws":1,"losses":0,"wins":29},"gpt-6-sol":{"draws":3,"losses":10,"wins":17},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":3},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":6},"meta/muse-spark-1.3":{"draws":0,"losses":1,"wins":9},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":0,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":2,"wins":4},"o3":{"draws":0,"losses":1,"wins":9},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":3,"wins":5},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":6},"qwen/qwen3.8-flash":{"draws":0,"losses":1,"wins":5},"qwen/qwen3.8-max":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.8-max-0902":{"draws":0,"losses":0,"wins":10},"stealth/ox-alpha":{"draws":0,"losses":1,"wins":13},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":5},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":4},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":12},"x-ai/grok-4.6":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":10},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":11},"z-ai/glm-5.2":{"draws":0,"losses":2,"wins":10},"z-ai/glm-5.3":{"draws":1,"losses":1,"wins":2},"z-ai/glm-5.3-flash":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.3-flashx":{"draws":1,"losses":5,"wins":18}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":9,"wins":2},"claude-fable-5":{"draws":2,"losses":12,"wins":6},"claude-fable-5-1":{"draws":0,"losses":18,"wins":0},"claude-opus-4-5":{"draws":32,"losses":35,"wins":9},"claude-opus-4-8":{"draws":18,"losses":32,"wins":10},"claude-opus-5":{"draws":10,"losses":41,"wins":5},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":6,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":11,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":20,"losses":15,"wins":13},"deepseek/deepseek-v4-pro":{"draws":5,"losses":11,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":5,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":12,"wins":0},"google/gemini-3.1-flash-lite":{"draws":11,"losses":7,"wins":22},"google/gemini-3.5-flash":{"draws":7,"losses":14,"wins":1},"google/gemini-3.5-flash-lite":{"draws":21,"losses":14,"wins":15},"google/gemini-3.6-flash":{"draws":17,"losses":19,"wins":0},"google/gemini-3.8-flash":{"draws":0,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":11,"losses":9,"wins":18},"gpt-4.1":{"draws":11,"losses":9,"wins":6},"gpt-5":{"draws":15,"losses":17,"wins":10},"gpt-5.4":{"draws":0,"losses":5,"wins":1},"gpt-5.4-mini":{"draws":26,"losses":18,"wins":12},"gpt-5.4-nano":{"draws":13,"losses":35,"wins":18},"gpt-5.5":{"draws":34,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":4,"losses":7,"wins":3},"gpt-5.6-terra":{"draws":7,"losses":9,"wins":4},"gpt-6-astra":{"draws":1,"losses":11,"wins":0},"gpt-6-luna":{"draws":8,"losses":5,"wins":1},"gpt-6-sol":{"draws":5,"losses":9,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":15,"losses":1,"wins":20},"meituan/longcat-2.0":{"draws":16,"losses":17,"wins":23},"meta/muse-glimmer-30b":{"draws":6,"losses":1,"wins":5},"meta/muse-spark-1.2":{"draws":2,"losses":8,"wins":4},"meta/muse-spark-1.3":{"draws":7,"losses":12,"wins":3},"minimax/minimax-m3":{"draws":16,"losses":9,"wins":19},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":15,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":16,"wins":4},"nex-agi/nex-n2-pro":{"draws":16,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":45,"losses":9,"wins":8},"o3":{"draws":8,"losses":20,"wins":2},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":3},"poolside/laguna-s-2.1":{"draws":23,"losses":10,"wins":17},"qwen/qwen3.7-max":{"draws":22,"losses":12,"wins":16},"qwen/qwen3.7-plus":{"draws":12,"losses":14,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":7,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":5,"wins":1},"qwen/qwen3.8-flash":{"draws":5,"losses":1,"wins":0},"qwen/qwen3.8-max":{"draws":8,"losses":3,"wins":1},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":14,"losses":26,"wins":6},"stepfun/step-3.7-flash":{"draws":16,"losses":3,"wins":13},"tencent/hy3-preview":{"draws":4,"losses":9,"wins":5},"tencent/hy4-preview":{"draws":8,"losses":10,"wins":2},"thinkingmachines/inkling":{"draws":18,"losses":11,"wins":11},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":2},"x-ai/grok-4.5":{"draws":12,"losses":19,"wins":1},"x-ai/grok-4.6":{"draws":5,"losses":9,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":46,"losses":19,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":14,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":11,"losses":17,"wins":6},"z-ai/glm-5.3":{"draws":4,"losses":6,"wins":0},"z-ai/glm-5.3-flash":{"draws":5,"losses":4,"wins":1},"z-ai/glm-5.3-flashx":{"draws":0,"losses":11,"wins":1}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":8,"wins":4},"claude-fable-5":{"draws":9,"losses":17,"wins":2},"claude-fable-5-1":{"draws":1,"losses":21,"wins":0},"claude-opus-4-5":{"draws":67,"losses":68,"wins":21},"claude-opus-4-8":{"draws":29,"losses":41,"wins":10},"claude-opus-5":{"draws":21,"losses":87,"wins":10},"claude-opus-5-5":{"draws":1,"losses":17,"wins":2},"claude-sonnet-5":{"draws":12,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":13,"losses":19,"wins":20},"deepseek/deepseek-v4-flash":{"draws":41,"losses":27,"wins":36},"deepseek/deepseek-v4-pro":{"draws":10,"losses":12,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":4,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":16,"wins":1},"google/gemini-3.1-flash-lite":{"draws":28,"losses":19,"wins":43},"google/gemini-3.5-flash":{"draws":19,"losses":14,"wins":7},"google/gemini-3.5-flash-lite":{"draws":33,"losses":15,"wins":26},"google/gemini-3.6-flash":{"draws":33,"losses":29,"wins":8},"google/gemini-3.8-flash":{"draws":16,"losses":13,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":23,"wins":20},"gpt-4.1":{"draws":10,"losses":10,"wins":6},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":26,"losses":29,"wins":17},"gpt-5.4":{"draws":14,"losses":9,"wins":3},"gpt-5.4-mini":{"draws":28,"losses":29,"wins":9},"gpt-5.4-nano":{"draws":28,"losses":45,"wins":45},"gpt-5.5":{"draws":49,"losses":34,"wins":5},"gpt-5.6-luna":{"draws":13,"losses":8,"wins":3},"gpt-5.6-sol":{"draws":1,"losses":19,"wins":0},"gpt-5.6-terra":{"draws":11,"losses":16,"wins":3},"gpt-6-astra":{"draws":1,"losses":15,"wins":0},"gpt-6-luna":{"draws":7,"losses":5,"wins":4},"gpt-6-sol":{"draws":2,"losses":9,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":17,"losses":2,"wins":7},"inclusionai/ling-3.0-flash":{"draws":15,"losses":15,"wins":18},"meituan/longcat-2.0":{"draws":39,"losses":35,"wins":36},"meta/muse-glimmer-30b":{"draws":6,"losses":9,"wins":7},"meta/muse-spark-1.2":{"draws":3,"losses":14,"wins":1},"meta/muse-spark-1.3":{"draws":5,"losses":18,"wins":1},"minimax/minimax-m3":{"draws":39,"losses":20,"wins":25},"mistralai/mistral-medium-3-5":{"draws":4,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":21,"losses":24,"wins":7},"moonshotai/kimi-k3":{"draws":15,"losses":18,"wins":3},"nex-agi/nex-n2-pro":{"draws":6,"losses":19,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":42,"losses":31,"wins":17},"o3":{"draws":18,"losses":40,"wins":4},"openai/gpt-oss-120b":{"draws":22,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":24,"losses":18,"wins":24},"qwen/qwen3.7-max":{"draws":33,"losses":28,"wins":15},"qwen/qwen3.7-plus":{"draws":43,"losses":23,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":12,"wins":2},"qwen/qwen3.8-27b":{"draws":8,"losses":7,"wins":1},"qwen/qwen3.8-flash":{"draws":8,"losses":8,"wins":0},"qwen/qwen3.8-max":{"draws":16,"losses":10,"wins":2},"qwen/qwen3.8-max-0902":{"draws":5,"losses":13,"wins":2},"stealth/ox-alpha":{"draws":20,"losses":34,"wins":10},"stepfun/step-3.7-flash":{"draws":26,"losses":15,"wins":9},"tencent/hy3-preview":{"draws":27,"losses":10,"wins":13},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":0},"thinkingmachines/inkling":{"draws":29,"losses":12,"wins":39},"thinkingmachines/inkling-small":{"draws":9,"losses":6,"wins":5},"x-ai/grok-4.5":{"draws":26,"losses":26,"wins":4},"x-ai/grok-4.6":{"draws":9,"losses":16,"wins":1},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":1},"x-ai/grok-build-0.1":{"draws":20,"losses":17,"wins":7},"xiaomi/mimo-v2.5":{"draws":97,"losses":41,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":23,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":11,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":52,"losses":52,"wins":22},"z-ai/glm-5.3":{"draws":7,"losses":7,"wins":0},"z-ai/glm-5.3-flash":{"draws":10,"losses":15,"wins":7},"z-ai/glm-5.3-flashx":{"draws":11,"losses":9,"wins":0}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":3,"wins":7},"claude-fable-5":{"draws":0,"losses":12,"wins":2},"claude-fable-5-1":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":13,"losses":28,"wins":31},"claude-opus-4-8":{"draws":9,"losses":29,"wins":14},"claude-opus-5":{"draws":14,"losses":29,"wins":3},"claude-opus-5-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":1,"losses":7,"wins":10},"cohere/north-mini-code":{"draws":5,"losses":8,"wins":13},"deepseek/deepseek-v4-flash":{"draws":9,"losses":8,"wins":13},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":11,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":3},"google/gemini-3.1-flash-lite":{"draws":11,"losses":5,"wins":32},"google/gemini-3.5-flash":{"draws":3,"losses":3,"wins":14},"google/gemini-3.5-flash-lite":{"draws":13,"losses":4,"wins":23},"google/gemini-3.6-flash":{"draws":12,"losses":22,"wins":16},"google/gemini-3.8-flash":{"draws":4,"losses":7,"wins":5},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":7},"gpt-4.1":{"draws":1,"losses":9,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":8,"losses":9,"wins":11},"gpt-5.4":{"draws":2,"losses":19,"wins":1},"gpt-5.4-mini":{"draws":4,"losses":9,"wins":7},"gpt-5.4-nano":{"draws":6,"losses":21,"wins":27},"gpt-5.5":{"draws":5,"losses":16,"wins":11},"gpt-5.6-luna":{"draws":5,"losses":6,"wins":11},"gpt-5.6-sol":{"draws":5,"losses":17,"wins":8},"gpt-5.6-terra":{"draws":2,"losses":8,"wins":4},"gpt-6-astra":{"draws":2,"losses":22,"wins":2},"gpt-6-luna":{"draws":2,"losses":2,"wins":0},"gpt-6-sol":{"draws":1,"losses":1,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":4,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":11},"meituan/longcat-2.0":{"draws":11,"losses":9,"wins":18},"meta/muse-glimmer-30b":{"draws":3,"losses":6,"wins":3},"meta/muse-spark-1.2":{"draws":2,"losses":11,"wins":15},"meta/muse-spark-1.3":{"draws":0,"losses":11,"wins":1},"minimax/minimax-m3":{"draws":8,"losses":10,"wins":10},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":14,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":11,"wins":13},"nex-agi/nex-n2-pro":{"draws":4,"losses":8,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":8,"wins":16},"o3":{"draws":5,"losses":15,"wins":34},"openai/gpt-oss-120b":{"draws":2,"losses":2,"wins":4},"poolside/laguna-s-2.1":{"draws":6,"losses":7,"wins":15},"qwen/qwen3.7-max":{"draws":9,"losses":15,"wins":8},"qwen/qwen3.7-plus":{"draws":9,"losses":5,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":9,"wins":7},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"wins":8},"qwen/qwen3.8-flash":{"draws":3,"losses":7,"wins":8},"qwen/qwen3.8-max":{"draws":1,"losses":7,"wins":4},"qwen/qwen3.8-max-0902":{"draws":0,"losses":3,"wins":3},"stealth/ox-alpha":{"draws":1,"losses":20,"wins":23},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":12},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":9},"tencent/hy4-preview":{"draws":2,"losses":10,"wins":2},"thinkingmachines/inkling":{"draws":8,"losses":7,"wins":15},"thinkingmachines/inkling-small":{"draws":4,"losses":2,"wins":4},"x-ai/grok-4.5":{"draws":5,"losses":18,"wins":23},"x-ai/grok-4.6":{"draws":4,"losses":11,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":10},"xiaomi/mimo-v2.5":{"draws":20,"losses":7,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":0},"z-ai/glm-5.2":{"draws":19,"losses":19,"wins":18},"z-ai/glm-5.3":{"draws":5,"losses":8,"wins":3},"z-ai/glm-5.3-flash":{"draws":0,"losses":7,"wins":3}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":3},"claude-fable-5":{"draws":1,"losses":6,"wins":3},"claude-fable-5-1":{"draws":1,"losses":12,"wins":5},"claude-opus-4-5":{"draws":1,"losses":3,"wins":6},"claude-opus-4-8":{"draws":1,"losses":3,"wins":6},"claude-opus-5":{"draws":1,"losses":7,"wins":2},"claude-opus-5-5":{"draws":1,"losses":12,"wins":1},"claude-sonnet-5":{"draws":3,"losses":3,"wins":4},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":13},"deepseek/deepseek-v4-pro":{"draws":1,"losses":1,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":6,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":7,"wins":7},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":5},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":2,"losses":12,"wins":8},"google/gemini-3.8-flash":{"draws":3,"losses":0,"wins":7},"gpt-4.1":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":5,"losses":1,"wins":4},"gpt-5.4":{"draws":0,"losses":6,"wins":6},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":7},"gpt-5.4-nano":{"draws":2,"losses":0,"wins":6},"gpt-5.5":{"draws":3,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":1,"losses":3,"wins":4},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"gpt-6-luna":{"draws":5,"losses":4,"wins":9},"gpt-6-sol":{"draws":6,"losses":12,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":1},"meta/muse-glimmer-30b":{"draws":3,"losses":1,"wins":4},"meta/muse-spark-1.2":{"draws":1,"losses":7,"wins":2},"meta/muse-spark-1.3":{"draws":4,"losses":6,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":5},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":8},"o3":{"draws":2,"losses":2,"wins":6},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":1,"wins":4},"qwen/qwen3.8-27b":{"draws":1,"losses":3,"wins":0},"qwen/qwen3.8-flash":{"draws":3,"losses":0,"wins":5},"qwen/qwen3.8-max":{"draws":2,"losses":5,"wins":9},"qwen/qwen3.8-max-0902":{"draws":7,"losses":13,"wins":22},"stealth/ox-alpha":{"draws":3,"losses":15,"wins":18},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":0,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":6},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":9},"x-ai/grok-4.5":{"draws":1,"losses":2,"wins":3},"x-ai/grok-4.6":{"draws":3,"losses":5,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":2,"wins":22},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":4,"wins":5},"z-ai/glm-5.2":{"draws":4,"losses":3,"wins":9},"z-ai/glm-5.3":{"draws":2,"losses":1,"wins":1},"z-ai/glm-5.3-flash":{"draws":3,"losses":3,"wins":6},"z-ai/glm-5.3-flashx":{"draws":4,"losses":14,"wins":22}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"wins":9},"claude-fable-5":{"draws":1,"losses":4,"wins":5},"claude-fable-5-1":{"draws":0,"losses":4,"wins":4},"claude-opus-4-5":{"draws":0,"losses":0,"wins":8},"claude-opus-4-8":{"draws":0,"losses":0,"wins":6},"claude-opus-5":{"draws":2,"losses":0,"wins":4},"claude-opus-5-5":{"draws":9,"losses":9,"wins":6},"claude-sonnet-5":{"draws":0,"losses":1,"wins":5},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":7},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":0,"wins":7},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":0,"losses":3,"wins":3},"google/gemini-3.5-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.6-flash":{"draws":1,"losses":0,"wins":7},"google/gemini-3.8-flash":{"draws":2,"losses":0,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":2,"wins":4},"gpt-5.4":{"draws":0,"losses":2,"wins":8},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":5},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":6},"gpt-5.5":{"draws":3,"losses":0,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":1,"wins":3},"gpt-5.6-sol":{"draws":6,"losses":1,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":8},"gpt-6-astra":{"draws":1,"losses":1,"wins":2},"gpt-6-luna":{"draws":8,"losses":3,"wins":15},"gpt-6-sol":{"draws":8,"losses":3,"wins":11},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":3},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":2},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":4},"meta/muse-spark-1.3":{"draws":1,"losses":0,"wins":3},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":3},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":1,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":3},"o3":{"draws":0,"losses":1,"wins":5},"openai/gpt-oss-120b":{"draws":0,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":0,"wins":5},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":2,"wins":3},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":2},"stealth/ox-alpha":{"draws":3,"losses":3,"wins":10},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":4},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":2,"wins":6},"x-ai/grok-4.6":{"draws":0,"losses":0,"wins":8},"x-ai/grok-4.7":{"draws":4,"losses":2,"wins":10},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":0,"wins":3},"z-ai/glm-5.2":{"draws":4,"losses":0,"wins":6},"z-ai/glm-5.3":{"draws":3,"losses":0,"wins":5},"z-ai/glm-5.3-flashx":{"draws":3,"losses":2,"wins":13}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":15,"wins":19},"claude-fable-5":{"draws":21,"losses":28,"wins":13},"claude-fable-5-1":{"draws":9,"losses":39,"wins":2},"claude-opus-4-5":{"draws":29,"losses":32,"wins":41},"claude-opus-4-8":{"draws":31,"losses":33,"wins":24},"claude-opus-5":{"draws":13,"losses":59,"wins":2},"claude-opus-5-5":{"draws":1,"losses":18,"wins":1},"claude-sonnet-5":{"draws":18,"losses":15,"wins":17},"cohere/north-mini-code":{"draws":15,"losses":11,"wins":16},"deepseek/deepseek-v4-flash":{"draws":40,"losses":15,"wins":29},"deepseek/deepseek-v4-pro":{"draws":26,"losses":20,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":24,"wins":23},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":14,"losses":4,"wins":14},"google/gemini-3.5-flash":{"draws":26,"losses":17,"wins":35},"google/gemini-3.5-flash-lite":{"draws":51,"losses":17,"wins":32},"google/gemini-3.6-flash":{"draws":26,"losses":32,"wins":40},"google/gemini-3.8-flash":{"draws":13,"losses":32,"wins":21},"google/gemma-4-31b-it":{"draws":14,"losses":4,"wins":8},"gpt-4.1":{"draws":7,"losses":4,"wins":11},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":23,"losses":17,"wins":16},"gpt-5.4":{"draws":15,"losses":14,"wins":15},"gpt-5.4-mini":{"draws":38,"losses":5,"wins":5},"gpt-5.4-nano":{"draws":26,"losses":16,"wins":24},"gpt-5.5":{"draws":29,"losses":24,"wins":13},"gpt-5.6-luna":{"draws":29,"losses":10,"wins":17},"gpt-5.6-sol":{"draws":10,"losses":34,"wins":16},"gpt-5.6-terra":{"draws":31,"losses":15,"wins":22},"gpt-6-astra":{"draws":6,"losses":44,"wins":4},"gpt-6-luna":{"draws":6,"losses":4,"wins":10},"gpt-6-sol":{"draws":3,"losses":20,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":19,"losses":3,"wins":22},"inclusionai/ling-3.0-flash":{"draws":22,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":14,"losses":16,"wins":26},"meta/muse-glimmer-30b":{"draws":19,"losses":11,"wins":20},"meta/muse-spark-1.2":{"draws":6,"losses":25,"wins":21},"meta/muse-spark-1.3":{"draws":13,"losses":14,"wins":19},"minimax/minimax-m3":{"draws":15,"losses":4,"wins":7},"mistralai/mistral-medium-3-5":{"draws":11,"losses":4,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":9,"losses":3,"wins":8},"moonshotai/kimi-k3":{"draws":23,"losses":12,"wins":13},"nex-agi/nex-n2-pro":{"draws":20,"losses":3,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":33,"losses":8,"wins":17},"o3":{"draws":13,"losses":23,"wins":40},"openai/gpt-oss-120b":{"draws":22,"losses":7,"wins":13},"poolside/laguna-s-2.1":{"draws":40,"losses":11,"wins":21},"qwen/qwen3.7-max":{"draws":14,"losses":3,"wins":13},"qwen/qwen3.7-plus":{"draws":16,"losses":5,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":21,"losses":24,"wins":17},"qwen/qwen3.8-27b":{"draws":10,"losses":15,"wins":19},"qwen/qwen3.8-flash":{"draws":18,"losses":14,"wins":8},"qwen/qwen3.8-max":{"draws":23,"losses":21,"wins":18},"qwen/qwen3.8-max-0902":{"draws":8,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":62,"losses":86,"wins":56},"stepfun/step-3.7-flash":{"draws":7,"losses":7,"wins":26},"tencent/hy3-preview":{"draws":18,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":21,"losses":28,"wins":13},"thinkingmachines/inkling":{"draws":25,"losses":8,"wins":27},"thinkingmachines/inkling-small":{"draws":21,"losses":11,"wins":26},"x-ai/grok-4.5":{"draws":12,"losses":18,"wins":30},"x-ai/grok-4.6":{"draws":14,"losses":33,"wins":17},"x-ai/grok-4.7":{"draws":2,"losses":8,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":42,"losses":13,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":9,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":1,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":41,"losses":28,"wins":27},"z-ai/glm-5.3":{"draws":12,"losses":28,"wins":10},"z-ai/glm-5.3-flash":{"draws":25,"losses":24,"wins":15},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":4}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":3,"wins":17},"claude-fable-5":{"draws":8,"losses":19,"wins":27},"claude-fable-5-1":{"draws":4,"losses":46,"wins":16},"claude-opus-4-5":{"draws":10,"losses":10,"wins":34},"claude-opus-4-8":{"draws":4,"losses":1,"wins":11},"claude-opus-5":{"draws":7,"losses":22,"wins":5},"claude-opus-5-5":{"draws":0,"losses":7,"wins":1},"claude-sonnet-5":{"draws":4,"losses":6,"wins":40},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":8,"losses":0,"wins":28},"deepseek/deepseek-v4-pro":{"draws":5,"losses":10,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":9,"wins":27},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":2,"wins":7},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":7},"google/gemini-3.5-flash":{"draws":8,"losses":13,"wins":39},"google/gemini-3.5-flash-lite":{"draws":8,"losses":3,"wins":53},"google/gemini-3.6-flash":{"draws":10,"losses":15,"wins":55},"google/gemini-3.8-flash":{"draws":10,"losses":12,"wins":34},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":8},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":5,"losses":0,"wins":7},"gpt-5.4":{"draws":6,"losses":20,"wins":30},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":8},"gpt-5.4-nano":{"draws":0,"losses":5,"wins":11},"gpt-5.5":{"draws":4,"losses":5,"wins":7},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":24},"gpt-5.6-sol":{"draws":13,"losses":26,"wins":23},"gpt-5.6-terra":{"draws":15,"losses":4,"wins":21},"gpt-6-astra":{"draws":10,"losses":37,"wins":3},"gpt-6-luna":{"draws":1,"losses":0,"wins":3},"gpt-6-sol":{"draws":1,"losses":4,"wins":5},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":11},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":19},"meta/muse-glimmer-30b":{"draws":1,"losses":2,"wins":17},"meta/muse-spark-1.2":{"draws":10,"losses":10,"wins":26},"meta/muse-spark-1.3":{"draws":11,"losses":13,"wins":30},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"moonshotai/kimi-k3":{"draws":5,"losses":13,"wins":28},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":8},"o3":{"draws":4,"losses":6,"wins":38},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":11},"poolside/laguna-s-2.1":{"draws":7,"losses":0,"wins":13},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":1,"losses":1,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":18,"wins":29},"qwen/qwen3.8-27b":{"draws":5,"losses":8,"wins":13},"qwen/qwen3.8-flash":{"draws":8,"losses":4,"wins":18},"qwen/qwen3.8-max":{"draws":10,"losses":8,"wins":26},"qwen/qwen3.8-max-0902":{"draws":5,"losses":3,"wins":8},"stealth/ox-alpha":{"draws":23,"losses":41,"wins":101},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":16},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":4,"losses":11,"wins":29},"thinkingmachines/inkling":{"draws":9,"losses":2,"wins":17},"thinkingmachines/inkling-small":{"draws":4,"losses":0,"wins":22},"x-ai/grok-4.5":{"draws":4,"losses":11,"wins":17},"x-ai/grok-4.6":{"draws":10,"losses":21,"wins":23},"x-ai/grok-4.7":{"draws":1,"losses":0,"wins":3},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":3,"wins":0},"z-ai/glm-5.2":{"draws":15,"losses":13,"wins":26},"z-ai/glm-5.3":{"draws":7,"losses":13,"wins":12},"z-ai/glm-5.3-flash":{"draws":9,"losses":11,"wins":28},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":2}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":6,"wins":11},"claude-fable-5":{"draws":8,"losses":29,"wins":17},"claude-fable-5-1":{"draws":7,"losses":53,"wins":6},"claude-opus-4-5":{"draws":15,"losses":7,"wins":24},"claude-opus-4-8":{"draws":1,"losses":3,"wins":4},"claude-opus-5":{"draws":1,"losses":34,"wins":7},"claude-opus-5-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":9,"losses":6,"wins":35},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":9,"losses":4,"wins":25},"deepseek/deepseek-v4-pro":{"draws":16,"losses":15,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":10,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":14,"losses":13,"wins":23},"google/gemini-3.5-flash-lite":{"draws":15,"losses":1,"wins":52},"google/gemini-3.6-flash":{"draws":16,"losses":20,"wins":38},"google/gemini-3.8-flash":{"draws":15,"losses":25,"wins":18},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":7},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":7,"losses":4,"wins":3},"gpt-5.4":{"draws":13,"losses":20,"wins":13},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":5},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":3},"gpt-5.5":{"draws":2,"losses":4,"wins":2},"gpt-5.6-luna":{"draws":10,"losses":12,"wins":16},"gpt-5.6-sol":{"draws":7,"losses":26,"wins":25},"gpt-5.6-terra":{"draws":13,"losses":14,"wins":23},"gpt-6-astra":{"draws":11,"losses":43,"wins":6},"gpt-6-luna":{"draws":0,"losses":0,"wins":6},"gpt-6-sol":{"draws":2,"losses":5,"wins":5},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":13,"losses":0,"wins":11},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":8},"meta/muse-glimmer-30b":{"draws":12,"losses":3,"wins":19},"meta/muse-spark-1.2":{"draws":6,"losses":12,"wins":8},"meta/muse-spark-1.3":{"draws":9,"losses":12,"wins":23},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":6},"mistralai/mistral-medium-3-5":{"draws":10,"losses":2,"wins":6},"moonshotai/kimi-k3":{"draws":16,"losses":12,"wins":20},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":8},"o3":{"draws":10,"losses":16,"wins":28},"openai/gpt-oss-120b":{"draws":12,"losses":0,"wins":22},"poolside/laguna-s-2.1":{"draws":15,"losses":5,"wins":18},"qwen/qwen3.7-max":{"draws":4,"losses":0,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":20,"wins":15},"qwen/qwen3.8-27b":{"draws":4,"losses":9,"wins":17},"qwen/qwen3.8-flash":{"draws":8,"losses":11,"wins":11},"qwen/qwen3.8-max":{"draws":13,"losses":18,"wins":15},"qwen/qwen3.8-max-0902":{"draws":0,"losses":0,"wins":2},"stealth/ox-alpha":{"draws":32,"losses":54,"wins":81},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":8},"tencent/hy4-preview":{"draws":6,"losses":16,"wins":18},"thinkingmachines/inkling":{"draws":7,"losses":2,"wins":21},"thinkingmachines/inkling-small":{"draws":19,"losses":3,"wins":26},"x-ai/grok-4.5":{"draws":4,"losses":13,"wins":19},"x-ai/grok-4.6":{"draws":13,"losses":19,"wins":22},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":1,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":4,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":23,"losses":6,"wins":21},"z-ai/glm-5.3":{"draws":12,"losses":30,"wins":10},"z-ai/glm-5.3-flash":{"draws":10,"losses":6,"wins":20},"z-ai/glm-5.3-flashx":{"draws":3,"losses":1,"wins":6}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":0,"wins":6},"claude-fable-5":{"draws":4,"losses":4,"wins":4},"claude-fable-5-1":{"draws":1,"losses":12,"wins":3},"claude-opus-4-5":{"draws":1,"losses":1,"wins":8},"claude-opus-4-8":{"draws":2,"losses":0,"wins":2},"claude-opus-5":{"draws":2,"losses":12,"wins":2},"claude-opus-5-5":{"draws":3,"losses":11,"wins":0},"claude-sonnet-5":{"draws":4,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":6},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":5,"wins":7},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":1,"losses":4,"wins":1},"google/gemini-3.5-flash-lite":{"draws":3,"losses":4,"wins":11},"google/gemini-3.6-flash":{"draws":7,"losses":7,"wins":2},"google/gemini-3.8-flash":{"draws":0,"losses":4,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-5":{"draws":4,"losses":1,"wins":5},"gpt-5.4":{"draws":5,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":3,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":5,"losses":2,"wins":3},"gpt-5.5":{"draws":7,"losses":6,"wins":1},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":3},"gpt-5.6-sol":{"draws":4,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":0},"gpt-6-astra":{"draws":0,"losses":9,"wins":1},"gpt-6-luna":{"draws":4,"losses":2,"wins":6},"gpt-6-sol":{"draws":4,"losses":12,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":10},"meituan/longcat-2.0":{"draws":6,"losses":3,"wins":3},"meta/muse-glimmer-30b":{"draws":2,"losses":4,"wins":2},"meta/muse-spark-1.2":{"draws":2,"losses":5,"wins":1},"meta/muse-spark-1.3":{"draws":5,"losses":2,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":8},"mistralai/mistral-medium-3-5":{"draws":3,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":4},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":7},"o3":{"draws":0,"losses":7,"wins":5},"openai/gpt-oss-120b":{"draws":1,"losses":2,"wins":9},"poolside/laguna-s-2.1":{"draws":2,"losses":4,"wins":6},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":2},"qwen/qwen3.8-flash":{"draws":1,"losses":2,"wins":7},"qwen/qwen3.8-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.8-max-0902":{"draws":7,"losses":19,"wins":12},"stealth/ox-alpha":{"draws":6,"losses":18,"wins":16},"stepfun/step-3.7-flash":{"draws":4,"losses":1,"wins":1},"tencent/hy3-preview":{"draws":1,"losses":2,"wins":1},"tencent/hy4-preview":{"draws":0,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":6},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":0,"losses":1,"wins":3},"x-ai/grok-4.6":{"draws":5,"losses":1,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":5,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":8,"losses":1,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":15,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":8,"wins":7},"z-ai/glm-5.2":{"draws":2,"losses":9,"wins":1},"z-ai/glm-5.3":{"draws":1,"losses":6,"wins":1},"z-ai/glm-5.3-flash":{"draws":1,"losses":5,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":11,"wins":3}}},"none":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":18,"wins":5},"claude-fable-5":{"draws":6,"losses":11,"wins":3},"claude-fable-5-1":{"draws":1,"losses":15,"wins":0},"claude-opus-4-5":{"draws":13,"losses":33,"wins":4},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":14,"wins":0},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":12,"losses":32,"wins":4},"cohere/north-mini-code":{"draws":1,"losses":3,"wins":2},"deepseek/deepseek-v4-flash":{"draws":16,"losses":25,"wins":7},"deepseek/deepseek-v4-pro":{"draws":13,"losses":20,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":19,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":6,"wins":3},"google/gemini-3.1-flash-lite":{"draws":6,"losses":4,"wins":6},"google/gemini-3.5-flash":{"draws":13,"losses":21,"wins":4},"google/gemini-3.5-flash-lite":{"draws":25,"losses":39,"wins":22},"google/gemini-3.6-flash":{"draws":18,"losses":31,"wins":11},"google/gemini-3.8-flash":{"draws":8,"losses":20,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":6,"wins":2},"gpt-5.4":{"draws":10,"losses":15,"wins":7},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":1,"losses":5,"wins":2},"gpt-5.5":{"draws":4,"losses":7,"wins":1},"gpt-5.6-luna":{"draws":11,"losses":19,"wins":14},"gpt-5.6-sol":{"draws":3,"losses":22,"wins":1},"gpt-5.6-terra":{"draws":9,"losses":26,"wins":3},"gpt-6-astra":{"draws":0,"losses":19,"wins":1},"gpt-6-luna":{"draws":1,"losses":4,"wins":3},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":14,"losses":9,"wins":13},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":7},"meituan/longcat-2.0":{"draws":10,"losses":7,"wins":5},"meta/muse-glimmer-30b":{"draws":21,"losses":15,"wins":12},"meta/muse-spark-1.2":{"draws":9,"losses":13,"wins":4},"meta/muse-spark-1.3":{"draws":4,"losses":18,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":5,"wins":5},"mistralai/mistral-medium-3-5":{"draws":17,"losses":7,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":16,"wins":6},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":3,"wins":5},"o3":{"draws":9,"losses":35,"wins":8},"openai/gpt-oss-120b":{"draws":17,"losses":21,"wins":12},"poolside/laguna-s-2.1":{"draws":9,"losses":9,"wins":10},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":21,"wins":4},"qwen/qwen3.8-27b":{"draws":7,"losses":14,"wins":5},"qwen/qwen3.8-flash":{"draws":13,"losses":13,"wins":2},"qwen/qwen3.8-max":{"draws":19,"losses":16,"wins":7},"qwen/qwen3.8-max-0902":{"draws":2,"losses":6,"wins":2},"stealth/ox-alpha":{"draws":24,"losses":72,"wins":18},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":9},"tencent/hy3-preview":{"draws":0,"losses":3,"wins":3},"tencent/hy4-preview":{"draws":14,"losses":16,"wins":4},"thinkingmachines/inkling":{"draws":13,"losses":18,"wins":13},"thinkingmachines/inkling-small":{"draws":17,"losses":11,"wins":16},"x-ai/grok-4.5":{"draws":7,"losses":22,"wins":5},"x-ai/grok-4.6":{"draws":9,"losses":14,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":4,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":5,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":3,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":10,"wins":1},"z-ai/glm-5.2":{"draws":34,"losses":11,"wins":11},"z-ai/glm-5.3":{"draws":8,"losses":18,"wins":2},"z-ai/glm-5.3-flash":{"draws":11,"losses":16,"wins":3},"z-ai/glm-5.3-flashx":{"draws":0,"losses":7,"wins":1}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":6,"wins":22},"claude-fable-5":{"draws":4,"losses":17,"wins":11},"claude-fable-5-1":{"draws":1,"losses":43,"wins":4},"claude-opus-4-5":{"draws":8,"losses":9,"wins":29},"claude-opus-4-8":{"draws":2,"losses":7,"wins":3},"claude-opus-5":{"draws":5,"losses":31,"wins":4},"claude-opus-5-5":{"draws":1,"losses":5,"wins":0},"claude-sonnet-5":{"draws":16,"losses":10,"wins":26},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":13,"losses":9,"wins":30},"deepseek/deepseek-v4-pro":{"draws":15,"losses":12,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":7,"wins":25},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":5,"wins":2},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":6},"google/gemini-3.5-flash":{"draws":13,"losses":12,"wins":21},"google/gemini-3.5-flash-lite":{"draws":23,"losses":11,"wins":42},"google/gemini-3.6-flash":{"draws":20,"losses":23,"wins":37},"google/gemini-3.8-flash":{"draws":10,"losses":20,"wins":18},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":0,"wins":7},"gpt-5.4":{"draws":18,"losses":18,"wins":20},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":14},"gpt-5.5":{"draws":6,"losses":3,"wins":7},"gpt-5.6-luna":{"draws":19,"losses":9,"wins":20},"gpt-5.6-sol":{"draws":9,"losses":28,"wins":13},"gpt-5.6-terra":{"draws":12,"losses":11,"wins":33},"gpt-6-astra":{"draws":2,"losses":36,"wins":12},"gpt-6-luna":{"draws":0,"losses":1,"wins":5},"gpt-6-sol":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":0,"wins":13},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":7,"losses":11,"wins":12},"meta/muse-glimmer-30b":{"draws":16,"losses":2,"wins":12},"meta/muse-spark-1.2":{"draws":10,"losses":12,"wins":14},"meta/muse-spark-1.3":{"draws":7,"losses":15,"wins":16},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":5},"mistralai/mistral-medium-3-5":{"draws":13,"losses":1,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":6,"wins":26},"nex-agi/nex-n2-pro":{"draws":1,"losses":1,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":7},"o3":{"draws":4,"losses":8,"wins":38},"openai/gpt-oss-120b":{"draws":14,"losses":4,"wins":16},"poolside/laguna-s-2.1":{"draws":11,"losses":4,"wins":13},"qwen/qwen3.7-max":{"draws":2,"losses":1,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":13,"wins":16},"qwen/qwen3.8-27b":{"draws":1,"losses":10,"wins":11},"qwen/qwen3.8-flash":{"draws":10,"losses":7,"wins":13},"qwen/qwen3.8-max":{"draws":9,"losses":17,"wins":22},"qwen/qwen3.8-max-0902":{"draws":5,"losses":1,"wins":2},"stealth/ox-alpha":{"draws":32,"losses":46,"wins":72},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":13},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":10,"losses":14,"wins":24},"thinkingmachines/inkling":{"draws":8,"losses":2,"wins":26},"thinkingmachines/inkling-small":{"draws":15,"losses":4,"wins":17},"x-ai/grok-4.5":{"draws":7,"losses":20,"wins":19},"x-ai/grok-4.6":{"draws":13,"losses":19,"wins":22},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.5":{"draws":7,"losses":1,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":2,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":9},"z-ai/glm-5.2":{"draws":21,"losses":15,"wins":20},"z-ai/glm-5.3":{"draws":8,"losses":34,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":23,"wins":12},"z-ai/glm-5.3-flashx":{"draws":6,"losses":6,"wins":2}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":25},"claude-fable-5":{"draws":1,"losses":12,"wins":33},"claude-fable-5-1":{"draws":3,"losses":35,"wins":12},"claude-opus-4-5":{"draws":3,"losses":0,"wins":35},"claude-opus-4-8":{"draws":0,"losses":2,"wins":6},"claude-opus-5":{"draws":6,"losses":12,"wins":6},"claude-opus-5-5":{"draws":1,"losses":10,"wins":5},"claude-sonnet-5":{"draws":6,"losses":2,"wins":44},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":1,"losses":0,"wins":33},"deepseek/deepseek-v4-pro":{"draws":3,"losses":1,"wins":30},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":1,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":1,"wins":18},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":15},"google/gemini-3.5-flash":{"draws":7,"losses":6,"wins":41},"google/gemini-3.5-flash-lite":{"draws":8,"losses":0,"wins":46},"google/gemini-3.6-flash":{"draws":3,"losses":4,"wins":61},"google/gemini-3.8-flash":{"draws":4,"losses":7,"wins":43},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":1,"losses":1,"wins":10},"gpt-5.4":{"draws":5,"losses":9,"wins":36},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":10},"gpt-5.5":{"draws":2,"losses":1,"wins":7},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":22},"gpt-5.6-sol":{"draws":9,"losses":9,"wins":34},"gpt-5.6-terra":{"draws":8,"losses":0,"wins":38},"gpt-6-astra":{"draws":9,"losses":37,"wins":12},"gpt-6-luna":{"draws":1,"losses":0,"wins":9},"gpt-6-sol":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":7},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":14},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":13},"meta/muse-spark-1.2":{"draws":3,"losses":0,"wins":31},"meta/muse-spark-1.3":{"draws":2,"losses":5,"wins":35},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":7},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":11},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":7,"losses":0,"wins":39},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":6},"o3":{"draws":0,"losses":3,"wins":33},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":18},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":24},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":11},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":2,"wins":37},"qwen/qwen3.8-27b":{"draws":2,"losses":1,"wins":19},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":19},"qwen/qwen3.8-max":{"draws":5,"losses":2,"wins":35},"qwen/qwen3.8-max-0902":{"draws":0,"losses":0,"wins":18},"stealth/ox-alpha":{"draws":25,"losses":8,"wins":121},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":9},"tencent/hy4-preview":{"draws":3,"losses":6,"wins":35},"thinkingmachines/inkling":{"draws":5,"losses":0,"wins":19},"thinkingmachines/inkling-small":{"draws":4,"losses":1,"wins":29},"x-ai/grok-4.5":{"draws":1,"losses":4,"wins":29},"x-ai/grok-4.6":{"draws":7,"losses":7,"wins":36},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":2,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":7},"z-ai/glm-5.2":{"draws":7,"losses":2,"wins":27},"z-ai/glm-5.3":{"draws":4,"losses":14,"wins":30},"z-ai/glm-5.3-flash":{"draws":12,"losses":3,"wins":33},"z-ai/glm-5.3-flashx":{"draws":3,"losses":2,"wins":9}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":4,"wins":8},"claude-fable-5":{"draws":4,"losses":10,"wins":4},"claude-fable-5-1":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":27,"losses":11,"wins":20},"claude-opus-4-8":{"draws":17,"losses":35,"wins":16},"claude-opus-5":{"draws":14,"losses":70,"wins":8},"claude-opus-5-5":{"draws":1,"losses":11,"wins":2},"claude-sonnet-5":{"draws":2,"losses":5,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":19},"deepseek/deepseek-v4-flash":{"draws":8,"losses":12,"wins":10},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":5,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":19},"google/gemini-3.5-flash":{"draws":9,"losses":7,"wins":8},"google/gemini-3.5-flash-lite":{"draws":22,"losses":16,"wins":16},"google/gemini-3.6-flash":{"draws":15,"losses":17,"wins":18},"google/gemini-3.8-flash":{"draws":5,"losses":4,"wins":1},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":18},"gpt-4.1":{"draws":10,"losses":7,"wins":3},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":13,"losses":0,"wins":3},"gpt-5.4":{"draws":1,"losses":2,"wins":1},"gpt-5.4-mini":{"draws":19,"losses":12,"wins":15},"gpt-5.4-nano":{"draws":15,"losses":15,"wins":32},"gpt-5.5":{"draws":26,"losses":14,"wins":6},"gpt-5.6-luna":{"draws":4,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":7,"losses":17,"wins":2},"gpt-5.6-terra":{"draws":12,"losses":0,"wins":2},"gpt-6-astra":{"draws":3,"losses":17,"wins":2},"gpt-6-luna":{"draws":5,"losses":5,"wins":4},"gpt-6-sol":{"draws":2,"losses":6,"wins":0},"inception/mercury-2.5-preview":{"draws":5,"losses":0,"wins":1},"inclusionai/ling-3.0-flash":{"draws":14,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":18,"losses":7,"wins":17},"meta/muse-glimmer-30b":{"draws":2,"losses":2,"wins":6},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":7,"wins":3},"minimax/minimax-m3":{"draws":8,"losses":5,"wins":9},"mistralai/mistral-medium-3-5":{"draws":0,"losses":2,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":4,"wins":8},"moonshotai/kimi-k3":{"draws":15,"losses":8,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":7,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":5,"wins":22},"o3":{"draws":7,"losses":13,"wins":14},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":21,"losses":6,"wins":11},"qwen/qwen3.7-max":{"draws":7,"losses":11,"wins":18},"qwen/qwen3.7-plus":{"draws":7,"losses":4,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":6,"wins":1},"qwen/qwen3.8-27b":{"draws":3,"losses":7,"wins":4},"qwen/qwen3.8-flash":{"draws":4,"losses":0,"wins":2},"qwen/qwen3.8-max":{"draws":13,"losses":8,"wins":3},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":27,"losses":25,"wins":14},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":9,"losses":6,"wins":15},"tencent/hy4-preview":{"draws":3,"losses":7,"wins":8},"thinkingmachines/inkling":{"draws":17,"losses":13,"wins":22},"thinkingmachines/inkling-small":{"draws":4,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":13,"losses":13,"wins":12},"x-ai/grok-4.6":{"draws":6,"losses":8,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":24,"losses":14,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":15,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":22,"wins":39},"z-ai/glm-5.3":{"draws":4,"losses":8,"wins":2},"z-ai/glm-5.3-flash":{"draws":5,"losses":9,"wins":4},"z-ai/glm-5.3-flashx":{"draws":2,"losses":2,"wins":0}},"claude-opus-4-8":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":4,"wins":0},"claude-fable-5":{"draws":0,"losses":6,"wins":4},"claude-fable-5-1":{"draws":2,"losses":10,"wins":0},"claude-opus-4-5":{"draws":20,"losses":14,"wins":26},"claude-opus-4-8":{"draws":12,"losses":9,"wins":9},"claude-opus-5":{"draws":13,"losses":37,"wins":12},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":28},"deepseek/deepseek-v4-flash":{"draws":11,"losses":0,"wins":17},"deepseek/deepseek-v4-pro":{"draws":2,"losses":7,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":7,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":7,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":3,"wins":21},"google/gemini-3.5-flash":{"draws":15,"losses":7,"wins":10},"google/gemini-3.5-flash-lite":{"draws":15,"losses":9,"wins":12},"google/gemini-3.6-flash":{"draws":15,"losses":19,"wins":12},"google/gemini-3.8-flash":{"draws":1,"losses":6,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":1,"wins":12},"gpt-4.1":{"draws":7,"losses":3,"wins":12},"gpt-5":{"draws":6,"losses":6,"wins":2},"gpt-5.4":{"draws":1,"losses":3,"wins":2},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":23},"gpt-5.4-nano":{"draws":11,"losses":17,"wins":26},"gpt-5.5":{"draws":13,"losses":24,"wins":11},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":4},"gpt-5.6-terra":{"draws":5,"losses":4,"wins":5},"gpt-6-astra":{"draws":2,"losses":8,"wins":0},"gpt-6-luna":{"draws":0,"losses":3,"wins":1},"gpt-6-sol":{"draws":1,"losses":3,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":17,"losses":0,"wins":9},"meituan/longcat-2.0":{"draws":3,"losses":6,"wins":13},"meta/muse-glimmer-30b":{"draws":2,"losses":2,"wins":4},"meta/muse-spark-1.2":{"draws":6,"losses":8,"wins":4},"meta/muse-spark-1.3":{"draws":1,"losses":6,"wins":1},"minimax/minimax-m3":{"draws":7,"losses":4,"wins":15},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":10,"losses":13,"wins":3},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":25},"o3":{"draws":1,"losses":11,"wins":10},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":16},"qwen/qwen3.7-max":{"draws":6,"losses":13,"wins":11},"qwen/qwen3.7-plus":{"draws":9,"losses":7,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":4,"wins":4},"qwen/qwen3.8-27b":{"draws":3,"losses":7,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":5,"wins":5},"qwen/qwen3.8-max":{"draws":5,"losses":8,"wins":7},"qwen/qwen3.8-max-0902":{"draws":3,"losses":7,"wins":0},"stealth/ox-alpha":{"draws":7,"losses":26,"wins":13},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":19},"tencent/hy3-preview":{"draws":10,"losses":3,"wins":9},"tencent/hy4-preview":{"draws":4,"losses":12,"wins":4},"thinkingmachines/inkling":{"draws":5,"losses":8,"wins":17},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":5},"x-ai/grok-4.5":{"draws":9,"losses":22,"wins":7},"x-ai/grok-4.6":{"draws":1,"losses":6,"wins":5},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":15,"wins":44},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":14,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":5,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":29,"losses":25,"wins":18},"z-ai/glm-5.3":{"draws":5,"losses":13,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":3,"wins":0},"z-ai/glm-5.3-flashx":{"draws":0,"losses":7,"wins":3}},"claude-opus-5":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":9,"wins":18},"claude-fable-5":{"draws":6,"losses":13,"wins":29},"claude-fable-5-1":{"draws":2,"losses":12,"wins":6},"claude-opus-4-5":{"draws":35,"losses":28,"wins":87},"claude-opus-4-8":{"draws":28,"losses":13,"wins":47},"claude-opus-5":{"draws":34,"losses":104,"wins":70},"claude-opus-5-5":{"draws":2,"losses":9,"wins":1},"claude-sonnet-5":{"draws":7,"losses":12,"wins":13},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":20},"deepseek/deepseek-v4-flash":{"draws":8,"losses":3,"wins":37},"deepseek/deepseek-v4-pro":{"draws":3,"losses":1,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":5,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":2,"wins":7},"google/gemini-3.1-flash-lite":{"draws":7,"losses":2,"wins":9},"google/gemini-3.5-flash":{"draws":6,"losses":6,"wins":34},"google/gemini-3.5-flash-lite":{"draws":11,"losses":6,"wins":67},"google/gemini-3.6-flash":{"draws":25,"losses":23,"wins":62},"google/gemini-3.8-flash":{"draws":8,"losses":15,"wins":17},"google/gemma-4-31b-it":{"draws":9,"losses":0,"wins":29},"gpt-4.1":{"draws":9,"losses":2,"wins":28},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":14,"losses":3,"wins":41},"gpt-5.4":{"draws":4,"losses":2,"wins":28},"gpt-5.4-mini":{"draws":17,"losses":5,"wins":24},"gpt-5.4-nano":{"draws":14,"losses":6,"wins":76},"gpt-5.5":{"draws":22,"losses":31,"wins":69},"gpt-5.6-luna":{"draws":5,"losses":3,"wins":20},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":25},"gpt-5.6-terra":{"draws":6,"losses":0,"wins":18},"gpt-6-astra":{"draws":4,"losses":18,"wins":4},"gpt-6-luna":{"draws":4,"losses":0,"wins":8},"gpt-6-sol":{"draws":4,"losses":4,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":1,"wins":12},"inclusionai/ling-3.0-flash":{"draws":20,"losses":1,"wins":35},"meituan/longcat-2.0":{"draws":14,"losses":6,"wins":64},"meta/muse-glimmer-30b":{"draws":4,"losses":3,"wins":11},"meta/muse-spark-1.2":{"draws":3,"losses":3,"wins":16},"meta/muse-spark-1.3":{"draws":10,"losses":7,"wins":15},"minimax/minimax-m3":{"draws":8,"losses":0,"wins":32},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":17},"moonshotai/kimi-k3":{"draws":10,"losses":16,"wins":30},"nex-agi/nex-n2-pro":{"draws":1,"losses":5,"wins":28},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":0,"wins":26},"o3":{"draws":4,"losses":3,"wins":41},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":10},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":72},"qwen/qwen3.7-max":{"draws":8,"losses":11,"wins":39},"qwen/qwen3.7-plus":{"draws":13,"losses":8,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":31},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":10},"qwen/qwen3.8-flash":{"draws":7,"losses":0,"wins":5},"qwen/qwen3.8-max":{"draws":10,"losses":9,"wins":21},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":9},"stealth/ox-alpha":{"draws":19,"losses":21,"wins":54},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":32},"tencent/hy3-preview":{"draws":14,"losses":2,"wins":28},"tencent/hy4-preview":{"draws":6,"losses":4,"wins":14},"thinkingmachines/inkling":{"draws":2,"losses":13,"wins":33},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":19},"x-ai/grok-4.5":{"draws":19,"losses":16,"wins":51},"x-ai/grok-4.6":{"draws":4,"losses":6,"wins":24},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":23,"losses":8,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":2,"wins":40},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":5},"z-ai/glm-5.2":{"draws":33,"losses":11,"wins":70},"z-ai/glm-5.3":{"draws":7,"losses":9,"wins":14},"z-ai/glm-5.3-flash":{"draws":0,"losses":8,"wins":22},"z-ai/glm-5.3-flashx":{"draws":6,"losses":5,"wins":7}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":4},"claude-fable-5":{"draws":2,"losses":1,"wins":5},"claude-fable-5-1":{"draws":2,"losses":8,"wins":4},"claude-opus-4-5":{"draws":5,"losses":3,"wins":14},"claude-opus-4-8":{"draws":0,"losses":3,"wins":7},"claude-opus-5":{"draws":2,"losses":7,"wins":9},"claude-opus-5-5":{"draws":1,"losses":33,"wins":10},"claude-sonnet-5":{"draws":1,"losses":2,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":5},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":13},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":11},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":1,"losses":3,"wins":10},"google/gemini-3.5-flash-lite":{"draws":5,"losses":0,"wins":11},"google/gemini-3.6-flash":{"draws":4,"losses":0,"wins":12},"google/gemini-3.8-flash":{"draws":3,"losses":2,"wins":7},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-4.1":{"draws":0,"losses":0,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":4},"gpt-5.4":{"draws":2,"losses":0,"wins":4},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":6},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":8},"gpt-5.5":{"draws":0,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":1,"wins":5},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":6},"gpt-6-astra":{"draws":1,"losses":7,"wins":2},"gpt-6-luna":{"draws":13,"losses":1,"wins":38},"gpt-6-sol":{"draws":8,"losses":26,"wins":20},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":0,"losses":0,"wins":8},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":4},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":4},"meta/muse-spark-1.3":{"draws":2,"losses":1,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":5},"moonshotai/kimi-k3":{"draws":0,"losses":4,"wins":4},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":12},"o3":{"draws":1,"losses":2,"wins":15},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":11},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-max":{"draws":5,"losses":0,"wins":7},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":13},"stealth/ox-alpha":{"draws":9,"losses":2,"wins":21},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":16},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":3},"x-ai/grok-4.5":{"draws":3,"losses":4,"wins":11},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":9,"wins":19},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":2,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":1,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":7,"wins":12},"z-ai/glm-5.2":{"draws":3,"losses":1,"wins":12},"z-ai/glm-5.3":{"draws":1,"losses":3,"wins":4},"z-ai/glm-5.3-flash":{"draws":4,"losses":0,"wins":8},"z-ai/glm-5.3-flashx":{"draws":9,"losses":6,"wins":27}},"claude-sonnet-5":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":15,"wins":18},"claude-fable-5":{"draws":14,"losses":27,"wins":3},"claude-fable-5-1":{"draws":5,"losses":41,"wins":2},"claude-opus-4-5":{"draws":28,"losses":40,"wins":10},"claude-opus-4-8":{"draws":5,"losses":4,"wins":1},"claude-opus-5":{"draws":3,"losses":13,"wins":6},"claude-opus-5-5":{"draws":0,"losses":5,"wins":1},"claude-sonnet-5":{"draws":19,"losses":34,"wins":15},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":23,"losses":18,"wins":27},"deepseek/deepseek-v4-pro":{"draws":19,"losses":17,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":19,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":9},"google/gemini-3.5-flash":{"draws":20,"losses":27,"wins":13},"google/gemini-3.5-flash-lite":{"draws":57,"losses":50,"wins":83},"google/gemini-3.6-flash":{"draws":37,"losses":75,"wins":42},"google/gemini-3.8-flash":{"draws":12,"losses":29,"wins":9},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":7},"gpt-4.1":{"draws":1,"losses":1,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":3,"losses":5,"wins":2},"gpt-5.4":{"draws":31,"losses":56,"wins":11},"gpt-5.4-mini":{"draws":4,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":4},"gpt-5.5":{"draws":4,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":41,"losses":29,"wins":36},"gpt-5.6-sol":{"draws":18,"losses":87,"wins":9},"gpt-5.6-terra":{"draws":22,"losses":22,"wins":10},"gpt-6-astra":{"draws":3,"losses":36,"wins":1},"gpt-6-sol":{"draws":0,"losses":9,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":23,"losses":3,"wins":18},"inclusionai/ling-3.0-flash":{"draws":10,"losses":4,"wins":22},"meituan/longcat-2.0":{"draws":18,"losses":9,"wins":29},"meta/muse-glimmer-30b":{"draws":19,"losses":10,"wins":21},"meta/muse-spark-1.2":{"draws":22,"losses":31,"wins":17},"meta/muse-spark-1.3":{"draws":18,"losses":20,"wins":6},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":15,"losses":4,"wins":17},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":33,"losses":43,"wins":16},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":6,"wins":3},"o3":{"draws":7,"losses":47,"wins":48},"openai/gpt-oss-120b":{"draws":23,"losses":7,"wins":26},"poolside/laguna-s-2.1":{"draws":16,"losses":6,"wins":28},"qwen/qwen3.7-max":{"draws":3,"losses":1,"wins":6},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":24,"wins":13},"qwen/qwen3.8-27b":{"draws":4,"losses":10,"wins":8},"qwen/qwen3.8-flash":{"draws":11,"losses":9,"wins":10},"qwen/qwen3.8-max":{"draws":19,"losses":20,"wins":7},"qwen/qwen3.8-max-0902":{"draws":1,"losses":3,"wins":0},"stealth/ox-alpha":{"draws":40,"losses":69,"wins":35},"stepfun/step-3.7-flash":{"draws":0,"losses":9,"wins":13},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":16,"losses":24,"wins":10},"thinkingmachines/inkling":{"draws":24,"losses":8,"wins":34},"thinkingmachines/inkling-small":{"draws":16,"losses":12,"wins":28},"x-ai/grok-4.5":{"draws":26,"losses":34,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":23,"wins":11},"x-ai/grok-4.7":{"draws":1,"losses":8,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":8,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":5,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":27,"losses":24,"wins":29},"z-ai/glm-5.3":{"draws":13,"losses":33,"wins":4},"z-ai/glm-5.3-flash":{"draws":12,"losses":17,"wins":15},"z-ai/glm-5.3-flashx":{"draws":2,"losses":0,"wins":0}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":0},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":7,"losses":19,"wins":4},"claude-opus-4-8":{"draws":4,"losses":36,"wins":0},"claude-opus-5":{"draws":4,"losses":28,"wins":4},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":0,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":4,"losses":13,"wins":5},"deepseek/deepseek-v4-flash":{"draws":12,"losses":15,"wins":3},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":13,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":11,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":13,"wins":19},"google/gemini-3.5-flash":{"draws":6,"losses":7,"wins":3},"google/gemini-3.5-flash-lite":{"draws":17,"losses":6,"wins":1},"google/gemini-3.6-flash":{"draws":11,"losses":27,"wins":8},"google/gemini-3.8-flash":{"draws":2,"losses":6,"wins":2},"google/gemma-4-31b-it":{"draws":5,"losses":9,"wins":2},"gpt-4.1":{"draws":4,"losses":8,"wins":2},"gpt-4.1-nano":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":8,"losses":8,"wins":6},"gpt-5.4":{"draws":0,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":11,"losses":11,"wins":4},"gpt-5.4-nano":{"draws":11,"losses":21,"wins":12},"gpt-5.5":{"draws":11,"losses":10,"wins":1},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":2,"losses":14,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":0,"losses":5,"wins":1},"gpt-6-sol":{"draws":1,"losses":3,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":19,"losses":5,"wins":0},"meituan/longcat-2.0":{"draws":22,"losses":14,"wins":2},"meta/muse-glimmer-30b":{"draws":2,"losses":10,"wins":2},"meta/muse-spark-1.2":{"draws":1,"losses":12,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":4,"wins":0},"minimax/minimax-m3":{"draws":0,"losses":23,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":13,"wins":1},"nex-agi/nex-n2-pro":{"draws":6,"losses":10,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":2,"wins":6},"o3":{"draws":14,"losses":5,"wins":7},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":23,"losses":1,"wins":8},"qwen/qwen3.7-max":{"draws":9,"losses":20,"wins":3},"qwen/qwen3.7-plus":{"draws":10,"losses":11,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":12,"wins":2},"qwen/qwen3.8-27b":{"draws":2,"losses":5,"wins":1},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":0},"qwen/qwen3.8-max":{"draws":1,"losses":6,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":7,"wins":0},"stealth/ox-alpha":{"draws":3,"losses":15,"wins":4},"stepfun/step-3.7-flash":{"draws":6,"losses":11,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":11,"wins":0},"tencent/hy4-preview":{"draws":4,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":7,"losses":17,"wins":8},"thinkingmachines/inkling-small":{"draws":4,"losses":4,"wins":2},"x-ai/grok-4.5":{"draws":3,"losses":15,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":3,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":5,"losses":5,"wins":0},"xiaomi/mimo-v2.5":{"draws":24,"losses":25,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":12,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":14,"losses":24,"wins":4},"z-ai/glm-5.3":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.3-flashx":{"draws":0,"losses":5,"wins":1}},"deepseek/deepseek-v4-flash":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":10,"wins":21},"claude-fable-5":{"draws":9,"losses":25,"wins":0},"claude-fable-5-1":{"draws":1,"losses":15,"wins":0},"claude-opus-4-5":{"draws":14,"losses":20,"wins":10},"claude-opus-4-8":{"draws":8,"losses":8,"wins":0},"claude-opus-5":{"draws":1,"losses":9,"wins":2},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":12,"losses":23,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":7,"losses":19,"wins":12},"deepseek/deepseek-v4-pro":{"draws":9,"losses":16,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":16,"losses":20,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":7,"wins":3},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":14,"losses":20,"wins":10},"google/gemini-3.5-flash-lite":{"draws":28,"losses":38,"wins":30},"google/gemini-3.6-flash":{"draws":15,"losses":47,"wins":10},"google/gemini-3.8-flash":{"draws":6,"losses":25,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":1},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":0,"losses":10,"wins":2},"gpt-5.4":{"draws":11,"losses":18,"wins":5},"gpt-5.4-mini":{"draws":2,"losses":3,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":5},"gpt-5.5":{"draws":2,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":15,"losses":20,"wins":17},"gpt-5.6-sol":{"draws":7,"losses":21,"wins":6},"gpt-5.6-terra":{"draws":14,"losses":20,"wins":6},"gpt-6-astra":{"draws":3,"losses":25,"wins":0},"gpt-6-luna":{"draws":1,"losses":3,"wins":2},"gpt-6-sol":{"draws":1,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":5,"losses":5,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":8,"wins":13},"meta/muse-glimmer-30b":{"draws":20,"losses":12,"wins":10},"meta/muse-spark-1.2":{"draws":5,"losses":13,"wins":6},"meta/muse-spark-1.3":{"draws":8,"losses":22,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":4},"mistralai/mistral-medium-3-5":{"draws":8,"losses":6,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":11,"wins":9},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":4},"o3":{"draws":7,"losses":31,"wins":22},"openai/gpt-oss-120b":{"draws":15,"losses":11,"wins":14},"poolside/laguna-s-2.1":{"draws":12,"losses":8,"wins":8},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":21,"wins":6},"qwen/qwen3.8-27b":{"draws":4,"losses":17,"wins":5},"qwen/qwen3.8-flash":{"draws":12,"losses":18,"wins":4},"qwen/qwen3.8-max":{"draws":15,"losses":18,"wins":7},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":3},"stealth/ox-alpha":{"draws":33,"losses":62,"wins":29},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":10,"losses":22,"wins":8},"thinkingmachines/inkling":{"draws":9,"losses":11,"wins":14},"thinkingmachines/inkling-small":{"draws":21,"losses":10,"wins":21},"x-ai/grok-4.5":{"draws":8,"losses":8,"wins":8},"x-ai/grok-4.6":{"draws":8,"losses":22,"wins":6},"x-ai/grok-4.7":{"draws":1,"losses":4,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":3,"losses":0,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":22,"losses":19,"wins":19},"z-ai/glm-5.3":{"draws":9,"losses":23,"wins":2},"z-ai/glm-5.3-flash":{"draws":14,"losses":9,"wins":5},"z-ai/glm-5.3-flashx":{"draws":1,"losses":6,"wins":1}},"deepseek/deepseek-v4-pro":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":14,"wins":10},"claude-fable-5":{"draws":7,"losses":12,"wins":3},"claude-fable-5-1":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":6,"losses":16,"wins":4},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":16,"wins":4},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":12,"losses":13,"wins":11},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":17,"losses":4,"wins":17},"deepseek/deepseek-v4-pro":{"draws":9,"losses":14,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":15,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":11,"losses":14,"wins":15},"google/gemini-3.5-flash-lite":{"draws":33,"losses":20,"wins":35},"google/gemini-3.6-flash":{"draws":28,"losses":17,"wins":11},"google/gemini-3.8-flash":{"draws":14,"losses":15,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":2,"wins":0},"gpt-5":{"draws":7,"losses":6,"wins":5},"gpt-5.4":{"draws":8,"losses":6,"wins":10},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":0,"wins":1},"gpt-5.5":{"draws":1,"losses":6,"wins":1},"gpt-5.6-luna":{"draws":12,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":5,"losses":14,"wins":3},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":8},"gpt-6-astra":{"draws":0,"losses":14,"wins":0},"gpt-6-luna":{"draws":1,"losses":3,"wins":0},"gpt-6-sol":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":11,"losses":6,"wins":9},"inclusionai/ling-3.0-flash":{"draws":9,"losses":2,"wins":9},"meituan/longcat-2.0":{"draws":9,"losses":5,"wins":18},"meta/muse-glimmer-30b":{"draws":16,"losses":9,"wins":11},"meta/muse-spark-1.2":{"draws":0,"losses":12,"wins":10},"meta/muse-spark-1.3":{"draws":7,"losses":12,"wins":7},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":10,"losses":6,"wins":8},"moonshotai/kimi-k3":{"draws":15,"losses":6,"wins":9},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":2},"o3":{"draws":12,"losses":13,"wins":13},"openai/gpt-oss-120b":{"draws":13,"losses":12,"wins":13},"poolside/laguna-s-2.1":{"draws":15,"losses":6,"wins":9},"qwen/qwen3.7-max":{"draws":4,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":16,"wins":8},"qwen/qwen3.8-27b":{"draws":9,"losses":11,"wins":4},"qwen/qwen3.8-flash":{"draws":10,"losses":5,"wins":9},"qwen/qwen3.8-max":{"draws":12,"losses":14,"wins":4},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":34,"losses":37,"wins":29},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":13,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":12,"losses":4,"wins":10},"thinkingmachines/inkling-small":{"draws":23,"losses":15,"wins":12},"x-ai/grok-4.5":{"draws":7,"losses":6,"wins":5},"x-ai/grok-4.6":{"draws":16,"losses":13,"wins":3},"x-ai/grok-4.7":{"draws":2,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":5,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":0,"wins":1},"z-ai/glm-5.2":{"draws":23,"losses":14,"wins":15},"z-ai/glm-5.3":{"draws":6,"losses":18,"wins":6},"z-ai/glm-5.3-flash":{"draws":11,"losses":14,"wins":5},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"wins":0}},"deepseek/deepseek-v4-pro-0813":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":12,"wins":5},"claude-fable-5":{"draws":6,"losses":18,"wins":2},"claude-fable-5-1":{"draws":1,"losses":25,"wins":0},"claude-opus-4-5":{"draws":9,"losses":21,"wins":4},"claude-opus-4-8":{"draws":0,"losses":10,"wins":2},"claude-opus-5":{"draws":1,"losses":10,"wins":1},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":10,"losses":11,"wins":3},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":20,"losses":11,"wins":17},"deepseek/deepseek-v4-pro":{"draws":24,"losses":5,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":8,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":4,"wins":0},"google/gemini-3.5-flash":{"draws":10,"losses":29,"wins":5},"google/gemini-3.5-flash-lite":{"draws":28,"losses":28,"wins":14},"google/gemini-3.6-flash":{"draws":25,"losses":24,"wins":9},"google/gemini-3.8-flash":{"draws":15,"losses":21,"wins":2},"gpt-4.1":{"draws":3,"losses":2,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":4,"losses":3,"wins":3},"gpt-5.4":{"draws":18,"losses":15,"wins":5},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":5},"gpt-5.5":{"draws":0,"losses":4,"wins":0},"gpt-5.6-luna":{"draws":12,"losses":10,"wins":10},"gpt-5.6-sol":{"draws":5,"losses":16,"wins":5},"gpt-5.6-terra":{"draws":13,"losses":16,"wins":5},"gpt-6-astra":{"draws":0,"losses":23,"wins":1},"gpt-6-luna":{"draws":2,"losses":2,"wins":2},"gpt-6-sol":{"draws":0,"losses":2,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":13,"losses":3,"wins":6},"inclusionai/ling-3.0-flash":{"draws":8,"losses":4,"wins":4},"meituan/longcat-2.0":{"draws":13,"losses":1,"wins":8},"meta/muse-glimmer-30b":{"draws":21,"losses":9,"wins":12},"meta/muse-spark-1.2":{"draws":6,"losses":12,"wins":2},"meta/muse-spark-1.3":{"draws":5,"losses":19,"wins":2},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":0},"mistralai/mistral-medium-3-5":{"draws":6,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":11,"losses":12,"wins":9},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":2},"o3":{"draws":12,"losses":14,"wins":18},"openai/gpt-oss-120b":{"draws":14,"losses":9,"wins":3},"poolside/laguna-s-2.1":{"draws":15,"losses":3,"wins":2},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":14,"wins":7},"qwen/qwen3.8-27b":{"draws":12,"losses":9,"wins":5},"qwen/qwen3.8-flash":{"draws":12,"losses":5,"wins":5},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":8},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":2},"stealth/ox-alpha":{"draws":45,"losses":49,"wins":24},"stepfun/step-3.7-flash":{"draws":6,"losses":1,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":2},"tencent/hy4-preview":{"draws":12,"losses":13,"wins":5},"thinkingmachines/inkling":{"draws":12,"losses":7,"wins":5},"thinkingmachines/inkling-small":{"draws":21,"losses":7,"wins":14},"x-ai/grok-4.5":{"draws":7,"losses":7,"wins":6},"x-ai/grok-4.6":{"draws":21,"losses":10,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":15,"losses":1,"wins":0},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":19,"losses":14,"wins":13},"z-ai/glm-5.3":{"draws":2,"losses":19,"wins":3},"z-ai/glm-5.3-flash":{"draws":15,"losses":8,"wins":9},"z-ai/glm-5.3-flashx":{"draws":0,"losses":4,"wins":0}},"deepseek/deepseek-v4.1-flash":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":5,"wins":4},"claude-fable-5":{"draws":5,"losses":9,"wins":0},"claude-fable-5-1":{"draws":0,"losses":17,"wins":1},"claude-opus-4-5":{"draws":5,"losses":4,"wins":1},"claude-opus-4-8":{"draws":1,"losses":7,"wins":2},"claude-opus-5":{"draws":4,"losses":4,"wins":0},"claude-opus-5-5":{"draws":0,"losses":14,"wins":0},"claude-sonnet-5":{"draws":5,"losses":2,"wins":1},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":6},"deepseek/deepseek-v4-flash":{"draws":9,"losses":4,"wins":9},"deepseek/deepseek-v4-pro":{"draws":4,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":2,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":16,"wins":6},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":11,"wins":5},"google/gemini-3.6-flash":{"draws":7,"losses":11,"wins":2},"google/gemini-3.8-flash":{"draws":2,"losses":3,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":3},"gpt-4.1":{"draws":2,"losses":3,"wins":1},"gpt-5":{"draws":2,"losses":5,"wins":1},"gpt-5.4":{"draws":2,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":1,"losses":5,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":3,"wins":1},"gpt-5.5":{"draws":5,"losses":2,"wins":1},"gpt-5.6-luna":{"draws":4,"losses":3,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":0,"wins":0},"gpt-6-astra":{"draws":2,"losses":10,"wins":0},"gpt-6-luna":{"draws":10,"losses":5,"wins":3},"gpt-6-sol":{"draws":2,"losses":8,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":4},"meituan/longcat-2.0":{"draws":7,"losses":5,"wins":6},"meta/muse-glimmer-30b":{"draws":7,"losses":3,"wins":2},"meta/muse-spark-1.2":{"draws":3,"losses":2,"wins":1},"meta/muse-spark-1.3":{"draws":7,"losses":4,"wins":1},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":5,"wins":1},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":1},"o3":{"draws":4,"losses":7,"wins":1},"openai/gpt-oss-120b":{"draws":7,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":3,"losses":3,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":3,"losses":9,"wins":2},"qwen/qwen3.8-27b":{"draws":2,"losses":5,"wins":1},"qwen/qwen3.8-flash":{"draws":3,"losses":5,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":5,"wins":2},"qwen/qwen3.8-max-0902":{"draws":8,"losses":11,"wins":1},"stealth/ox-alpha":{"draws":7,"losses":21,"wins":8},"stepfun/step-3.7-flash":{"draws":2,"losses":4,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":1},"tencent/hy4-preview":{"draws":4,"losses":3,"wins":3},"thinkingmachines/inkling":{"draws":7,"losses":0,"wins":1},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":1,"losses":7,"wins":0},"x-ai/grok-4.6":{"draws":5,"losses":4,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":6,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":9,"losses":8,"wins":3},"z-ai/glm-5.3":{"draws":3,"losses":7,"wins":2},"z-ai/glm-5.3-flash":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.3-flashx":{"draws":7,"losses":11,"wins":0}},"google/gemini-3.1-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":5,"wins":3},"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-fable-5-1":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":9,"losses":17,"wins":2},"claude-opus-4-8":{"draws":2,"losses":10,"wins":0},"claude-opus-5":{"draws":6,"losses":9,"wins":1},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":2,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":13,"wins":5},"deepseek/deepseek-v4-flash":{"draws":11,"losses":23,"wins":12},"deepseek/deepseek-v4-pro":{"draws":2,"losses":5,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":4,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":10,"wins":3},"google/gemini-3.1-flash-lite":{"draws":0,"losses":12,"wins":8},"google/gemini-3.5-flash":{"draws":0,"losses":9,"wins":1},"google/gemini-3.5-flash-lite":{"draws":3,"losses":14,"wins":1},"google/gemini-3.6-flash":{"draws":2,"losses":10,"wins":0},"google/gemini-3.8-flash":{"draws":2,"losses":0,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":8,"wins":12},"gpt-4.1":{"draws":5,"losses":9,"wins":0},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":10,"losses":10,"wins":0},"gpt-5.4":{"draws":0,"losses":4,"wins":0},"gpt-5.4-mini":{"draws":7,"losses":8,"wins":1},"gpt-5.4-nano":{"draws":2,"losses":11,"wins":9},"gpt-5.5":{"draws":8,"losses":7,"wins":1},"gpt-5.6-luna":{"draws":1,"losses":1,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":11,"wins":0},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"gpt-6-luna":{"draws":1,"losses":3,"wins":4},"gpt-6-sol":{"draws":1,"losses":9,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":1,"losses":11,"wins":8},"meituan/longcat-2.0":{"draws":3,"losses":18,"wins":5},"meta/muse-glimmer-30b":{"draws":6,"losses":4,"wins":0},"meta/muse-spark-1.2":{"draws":2,"losses":2,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":0},"minimax/minimax-m3":{"draws":6,"losses":12,"wins":10},"mistralai/mistral-medium-3-5":{"draws":2,"losses":6,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":10,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":26,"wins":6},"o3":{"draws":0,"losses":16,"wins":0},"openai/gpt-oss-120b":{"draws":2,"losses":6,"wins":2},"poolside/laguna-s-2.1":{"draws":2,"losses":10,"wins":4},"qwen/qwen3.7-max":{"draws":8,"losses":8,"wins":2},"qwen/qwen3.7-plus":{"draws":9,"losses":15,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.8-flash":{"draws":3,"losses":6,"wins":1},"qwen/qwen3.8-max":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":1,"losses":13,"wins":0},"stealth/ox-alpha":{"draws":5,"losses":9,"wins":2},"stepfun/step-3.7-flash":{"draws":4,"losses":17,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":9,"wins":1},"tencent/hy4-preview":{"draws":0,"losses":8,"wins":0},"thinkingmachines/inkling":{"draws":12,"losses":11,"wins":7},"thinkingmachines/inkling-small":{"draws":5,"losses":6,"wins":1},"x-ai/grok-4.5":{"draws":1,"losses":12,"wins":1},"x-ai/grok-4.6":{"draws":1,"losses":1,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":14,"losses":35,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":15,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":30,"wins":4},"z-ai/glm-5.3":{"draws":1,"losses":5,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.3-flashx":{"draws":3,"losses":7,"wins":0}},"google/gemini-3.5-flash":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":21,"wins":17},"claude-fable-5":{"draws":12,"losses":23,"wins":5},"claude-fable-5-1":{"draws":3,"losses":25,"wins":0},"claude-opus-4-5":{"draws":16,"losses":31,"wins":21},"claude-opus-4-8":{"draws":22,"losses":20,"wins":2},"claude-opus-5":{"draws":6,"losses":43,"wins":7},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":24,"losses":30,"wins":14},"cohere/north-mini-code":{"draws":7,"losses":3,"wins":6},"deepseek/deepseek-v4-flash":{"draws":30,"losses":25,"wins":21},"deepseek/deepseek-v4-pro":{"draws":19,"losses":28,"wins":15},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":23,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":6,"wins":4},"google/gemini-3.1-flash-lite":{"draws":9,"losses":8,"wins":17},"google/gemini-3.5-flash":{"draws":11,"losses":21,"wins":4},"google/gemini-3.5-flash-lite":{"draws":46,"losses":53,"wins":37},"google/gemini-3.6-flash":{"draws":28,"losses":43,"wins":21},"google/gemini-3.8-flash":{"draws":12,"losses":36,"wins":2},"google/gemma-4-31b-it":{"draws":12,"losses":1,"wins":7},"gpt-4.1":{"draws":4,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":9,"losses":17,"wins":12},"gpt-5.4":{"draws":8,"losses":19,"wins":11},"gpt-5.4-mini":{"draws":9,"losses":7,"wins":8},"gpt-5.4-nano":{"draws":16,"losses":17,"wins":23},"gpt-5.5":{"draws":10,"losses":14,"wins":4},"gpt-5.6-luna":{"draws":27,"losses":19,"wins":14},"gpt-5.6-sol":{"draws":5,"losses":30,"wins":7},"gpt-5.6-terra":{"draws":21,"losses":22,"wins":7},"gpt-6-astra":{"draws":2,"losses":33,"wins":1},"gpt-6-luna":{"draws":5,"losses":12,"wins":7},"gpt-6-sol":{"draws":3,"losses":13,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":12},"inclusionai/ling-3.0-flash":{"draws":15,"losses":3,"wins":18},"meituan/longcat-2.0":{"draws":10,"losses":10,"wins":30},"meta/muse-glimmer-30b":{"draws":22,"losses":17,"wins":15},"meta/muse-spark-1.2":{"draws":12,"losses":15,"wins":9},"meta/muse-spark-1.3":{"draws":8,"losses":30,"wins":6},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":14,"losses":8,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":25,"losses":9,"wins":12},"nex-agi/nex-n2-pro":{"draws":7,"losses":4,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":8,"wins":5},"o3":{"draws":13,"losses":33,"wins":34},"openai/gpt-oss-120b":{"draws":19,"losses":17,"wins":16},"poolside/laguna-s-2.1":{"draws":26,"losses":12,"wins":10},"qwen/qwen3.7-max":{"draws":10,"losses":13,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":29,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":19,"wins":6},"qwen/qwen3.8-flash":{"draws":20,"losses":8,"wins":10},"qwen/qwen3.8-max":{"draws":21,"losses":11,"wins":14},"qwen/qwen3.8-max-0902":{"draws":6,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":32,"losses":91,"wins":27},"stepfun/step-3.7-flash":{"draws":8,"losses":10,"wins":10},"tencent/hy3-preview":{"draws":2,"losses":7,"wins":7},"tencent/hy4-preview":{"draws":19,"losses":28,"wins":9},"thinkingmachines/inkling":{"draws":16,"losses":22,"wins":18},"thinkingmachines/inkling-small":{"draws":25,"losses":12,"wins":27},"x-ai/grok-4.5":{"draws":11,"losses":27,"wins":6},"x-ai/grok-4.6":{"draws":12,"losses":24,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":13,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":11,"losses":15,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":12,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":7,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":6,"wins":1},"z-ai/glm-5.2":{"draws":43,"losses":33,"wins":18},"z-ai/glm-5.3":{"draws":9,"losses":32,"wins":5},"z-ai/glm-5.3-flash":{"draws":14,"losses":14,"wins":8},"z-ai/glm-5.3-flashx":{"draws":7,"losses":4,"wins":3}},"google/gemini-3.5-flash-lite":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":31,"wins":34},"claude-fable-5":{"draws":19,"losses":59,"wins":14},"claude-fable-5-1":{"draws":9,"losses":74,"wins":1},"claude-opus-4-5":{"draws":64,"losses":68,"wins":58},"claude-opus-4-8":{"draws":9,"losses":15,"wins":10},"claude-opus-5":{"draws":12,"losses":89,"wins":9},"claude-opus-5-5":{"draws":1,"losses":13,"wins":0},"claude-sonnet-5":{"draws":57,"losses":91,"wins":46},"cohere/north-mini-code":{"draws":13,"losses":3,"wins":6},"deepseek/deepseek-v4-flash":{"draws":37,"losses":32,"wins":43},"deepseek/deepseek-v4-pro":{"draws":37,"losses":43,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":35,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":13,"wins":7},"google/gemini-3.1-flash-lite":{"draws":6,"losses":3,"wins":17},"google/gemini-3.5-flash":{"draws":37,"losses":42,"wins":29},"google/gemini-3.5-flash-lite":{"draws":132,"losses":109,"wins":125},"google/gemini-3.6-flash":{"draws":138,"losses":161,"wins":93},"google/gemini-3.8-flash":{"draws":23,"losses":59,"wins":4},"google/gemma-4-31b-it":{"draws":6,"losses":8,"wins":12},"gpt-4.1":{"draws":6,"losses":5,"wins":13},"gpt-4.1-nano":{"draws":0,"losses":7,"wins":7},"gpt-5":{"draws":14,"losses":7,"wins":5},"gpt-5.4":{"draws":54,"losses":91,"wins":19},"gpt-5.4-mini":{"draws":9,"losses":10,"wins":9},"gpt-5.4-nano":{"draws":17,"losses":14,"wins":25},"gpt-5.5":{"draws":17,"losses":6,"wins":5},"gpt-5.6-luna":{"draws":64,"losses":64,"wins":68},"gpt-5.6-sol":{"draws":19,"losses":131,"wins":26},"gpt-5.6-terra":{"draws":32,"losses":36,"wins":30},"gpt-6-astra":{"draws":2,"losses":76,"wins":0},"gpt-6-luna":{"draws":4,"losses":14,"wins":8},"gpt-6-sol":{"draws":3,"losses":25,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":45,"losses":5,"wins":28},"inclusionai/ling-3.0-flash":{"draws":50,"losses":6,"wins":70},"meituan/longcat-2.0":{"draws":47,"losses":46,"wins":88},"meta/muse-glimmer-30b":{"draws":39,"losses":16,"wins":29},"meta/muse-spark-1.2":{"draws":41,"losses":54,"wins":29},"meta/muse-spark-1.3":{"draws":15,"losses":46,"wins":23},"minimax/minimax-m3":{"draws":5,"losses":8,"wins":7},"mistralai/mistral-medium-3-5":{"draws":23,"losses":8,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":74,"losses":94,"wins":42},"nex-agi/nex-n2-pro":{"draws":10,"losses":3,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":10},"o3":{"draws":43,"losses":88,"wins":101},"openai/gpt-oss-120b":{"draws":31,"losses":23,"wins":34},"poolside/laguna-s-2.1":{"draws":76,"losses":50,"wins":54},"qwen/qwen3.7-max":{"draws":9,"losses":5,"wins":16},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":26,"losses":37,"wins":17},"qwen/qwen3.8-27b":{"draws":15,"losses":26,"wins":13},"qwen/qwen3.8-flash":{"draws":21,"losses":23,"wins":18},"qwen/qwen3.8-max":{"draws":27,"losses":28,"wins":27},"qwen/qwen3.8-max-0902":{"draws":5,"losses":9,"wins":2},"stealth/ox-alpha":{"draws":73,"losses":121,"wins":66},"stepfun/step-3.7-flash":{"draws":14,"losses":15,"wins":23},"tencent/hy3-preview":{"draws":18,"losses":10,"wins":4},"tencent/hy4-preview":{"draws":37,"losses":38,"wins":17},"thinkingmachines/inkling":{"draws":78,"losses":53,"wins":71},"thinkingmachines/inkling-small":{"draws":43,"losses":27,"wins":44},"x-ai/grok-4.5":{"draws":49,"losses":102,"wins":51},"x-ai/grok-4.6":{"draws":22,"losses":47,"wins":17},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":3},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":15,"losses":14,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":9,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":53,"losses":42,"wins":35},"z-ai/glm-5.3":{"draws":13,"losses":65,"wins":8},"z-ai/glm-5.3-flash":{"draws":26,"losses":53,"wins":19},"z-ai/glm-5.3-flashx":{"draws":4,"losses":8,"wins":2}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":33,"losses":32,"wins":39},"claude-fable-5":{"draws":22,"losses":37,"wins":11},"claude-fable-5-1":{"draws":4,"losses":72,"wins":0},"claude-opus-4-5":{"draws":68,"losses":83,"wins":41},"claude-opus-4-8":{"draws":11,"losses":13,"wins":10},"claude-opus-5":{"draws":11,"losses":68,"wins":11},"claude-opus-5-5":{"draws":1,"losses":21,"wins":0},"claude-sonnet-5":{"draws":65,"losses":81,"wins":48},"cohere/north-mini-code":{"draws":11,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":52,"losses":33,"wins":37},"deepseek/deepseek-v4-pro":{"draws":29,"losses":38,"wins":19},"deepseek/deepseek-v4-pro-0813":{"draws":38,"losses":35,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":4,"losses":2,"wins":8},"google/gemini-3.5-flash":{"draws":33,"losses":37,"wins":22},"google/gemini-3.5-flash-lite":{"draws":196,"losses":132,"wins":136},"google/gemini-3.6-flash":{"draws":90,"losses":157,"wins":57},"google/gemini-3.8-flash":{"draws":25,"losses":44,"wins":14},"google/gemma-4-31b-it":{"draws":10,"losses":8,"wins":2},"gpt-4.1":{"draws":14,"losses":7,"wins":7},"gpt-4.1-nano":{"draws":4,"losses":10,"wins":0},"gpt-5":{"draws":11,"losses":14,"wins":9},"gpt-5.4":{"draws":55,"losses":78,"wins":33},"gpt-5.4-mini":{"draws":18,"losses":6,"wins":10},"gpt-5.4-nano":{"draws":23,"losses":19,"wins":12},"gpt-5.5":{"draws":20,"losses":16,"wins":12},"gpt-5.6-luna":{"draws":84,"losses":52,"wins":70},"gpt-5.6-sol":{"draws":28,"losses":126,"wins":16},"gpt-5.6-terra":{"draws":38,"losses":32,"wins":24},"gpt-6-astra":{"draws":6,"losses":58,"wins":0},"gpt-6-luna":{"draws":5,"losses":0,"wins":3},"gpt-6-sol":{"draws":3,"losses":14,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":5,"losses":0,"wins":9},"inception/mercury-2.5-preview":{"draws":38,"losses":5,"wins":39},"inclusionai/ling-3.0-flash":{"draws":69,"losses":31,"wins":46},"meituan/longcat-2.0":{"draws":57,"losses":42,"wins":71},"meta/muse-glimmer-30b":{"draws":55,"losses":18,"wins":37},"meta/muse-spark-1.2":{"draws":33,"losses":81,"wins":28},"meta/muse-spark-1.3":{"draws":25,"losses":40,"wins":15},"minimax/minimax-m3":{"draws":8,"losses":8,"wins":20},"mistralai/mistral-medium-3-5":{"draws":31,"losses":8,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":89,"losses":105,"wins":28},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":5,"wins":9},"o3":{"draws":53,"losses":140,"wins":69},"openai/gpt-oss-120b":{"draws":44,"losses":18,"wins":34},"poolside/laguna-s-2.1":{"draws":106,"losses":41,"wins":53},"qwen/qwen3.7-max":{"draws":14,"losses":6,"wins":16},"qwen/qwen3.7-plus":{"draws":11,"losses":8,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":35,"losses":32,"wins":21},"qwen/qwen3.8-27b":{"draws":12,"losses":19,"wins":23},"qwen/qwen3.8-flash":{"draws":34,"losses":17,"wins":15},"qwen/qwen3.8-max":{"draws":36,"losses":49,"wins":25},"qwen/qwen3.8-max-0902":{"draws":7,"losses":2,"wins":3},"stealth/ox-alpha":{"draws":84,"losses":142,"wins":81},"stepfun/step-3.7-flash":{"draws":11,"losses":17,"wins":30},"tencent/hy3-preview":{"draws":10,"losses":7,"wins":11},"tencent/hy4-preview":{"draws":30,"losses":51,"wins":23},"thinkingmachines/inkling":{"draws":103,"losses":30,"wins":101},"thinkingmachines/inkling-small":{"draws":44,"losses":36,"wins":33},"x-ai/grok-4.5":{"draws":49,"losses":98,"wins":59},"x-ai/grok-4.6":{"draws":29,"losses":34,"wins":11},"x-ai/grok-4.7":{"draws":0,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":25,"losses":16,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":11,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":11,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.2":{"draws":46,"losses":42,"wins":32},"z-ai/glm-5.3":{"draws":14,"losses":61,"wins":5},"z-ai/glm-5.3-flash":{"draws":28,"losses":41,"wins":21},"z-ai/glm-5.3-flashx":{"draws":11,"losses":5,"wins":4}},"google/gemini-3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":12,"wins":15},"claude-fable-5":{"draws":7,"losses":29,"wins":10},"claude-fable-5-1":{"draws":4,"losses":53,"wins":1},"claude-opus-4-5":{"draws":16,"losses":10,"wins":22},"claude-opus-4-8":{"draws":2,"losses":10,"wins":4},"claude-opus-5":{"draws":8,"losses":15,"wins":9},"claude-opus-5-5":{"draws":2,"losses":10,"wins":0},"claude-sonnet-5":{"draws":15,"losses":9,"wins":18},"cohere/north-mini-code":{"draws":0,"losses":6,"wins":4},"deepseek/deepseek-v4-flash":{"draws":11,"losses":9,"wins":28},"deepseek/deepseek-v4-pro":{"draws":10,"losses":8,"wins":26},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":18,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":3,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":11,"losses":25,"wins":20},"google/gemini-3.5-flash-lite":{"draws":15,"losses":6,"wins":45},"google/gemini-3.6-flash":{"draws":19,"losses":31,"wins":34},"google/gemini-3.8-flash":{"draws":13,"losses":11,"wins":12},"google/gemma-4-31b-it":{"draws":3,"losses":0,"wins":3},"gpt-4.1":{"draws":2,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":4,"wins":8},"gpt-5.4":{"draws":12,"losses":18,"wins":14},"gpt-5.4-mini":{"draws":2,"losses":6,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":15},"gpt-5.5":{"draws":4,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":15,"losses":12,"wins":19},"gpt-5.6-sol":{"draws":7,"losses":28,"wins":17},"gpt-5.6-terra":{"draws":20,"losses":13,"wins":21},"gpt-6-astra":{"draws":8,"losses":44,"wins":4},"gpt-6-luna":{"draws":4,"losses":2,"wins":2},"gpt-6-sol":{"draws":1,"losses":5,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":17,"losses":1,"wins":12},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":8,"losses":4,"wins":12},"meta/muse-glimmer-30b":{"draws":15,"losses":7,"wins":20},"meta/muse-spark-1.2":{"draws":10,"losses":14,"wins":14},"meta/muse-spark-1.3":{"draws":3,"losses":16,"wins":19},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":6,"losses":3,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":17,"losses":11,"wins":16},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":6},"o3":{"draws":6,"losses":16,"wins":26},"openai/gpt-oss-120b":{"draws":9,"losses":2,"wins":13},"poolside/laguna-s-2.1":{"draws":9,"losses":4,"wins":27},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":9},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":15,"wins":19},"qwen/qwen3.8-27b":{"draws":8,"losses":9,"wins":19},"qwen/qwen3.8-flash":{"draws":6,"losses":8,"wins":14},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":21},"qwen/qwen3.8-max-0902":{"draws":1,"losses":0,"wins":3},"stealth/ox-alpha":{"draws":48,"losses":61,"wins":50},"stepfun/step-3.7-flash":{"draws":2,"losses":1,"wins":11},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":5},"tencent/hy4-preview":{"draws":10,"losses":19,"wins":11},"thinkingmachines/inkling":{"draws":11,"losses":6,"wins":17},"thinkingmachines/inkling-small":{"draws":19,"losses":8,"wins":25},"x-ai/grok-4.5":{"draws":6,"losses":24,"wins":10},"x-ai/grok-4.6":{"draws":17,"losses":15,"wins":14},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":8,"losses":1,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":18,"losses":19,"wins":27},"z-ai/glm-5.3":{"draws":5,"losses":24,"wins":5},"z-ai/glm-5.3-flash":{"draws":11,"losses":19,"wins":18},"z-ai/glm-5.3-flashx":{"draws":0,"losses":8,"wins":4}},"google/gemma-4-31b-it":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":1},"claude-fable-5":{"draws":0,"losses":2,"wins":0},"claude-fable-5-1":{"draws":2,"losses":12,"wins":0},"claude-opus-4-5":{"draws":13,"losses":23,"wins":4},"claude-opus-4-8":{"draws":17,"losses":26,"wins":1},"claude-opus-5":{"draws":9,"losses":32,"wins":9},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":5,"losses":9,"wins":2},"cohere/north-mini-code":{"draws":9,"losses":6,"wins":11},"deepseek/deepseek-v4-flash":{"draws":14,"losses":29,"wins":11},"deepseek/deepseek-v4-pro":{"draws":0,"losses":8,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":4,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":12,"losses":19,"wins":23},"google/gemini-3.5-flash":{"draws":6,"losses":4,"wins":0},"google/gemini-3.5-flash-lite":{"draws":13,"losses":9,"wins":8},"google/gemini-3.6-flash":{"draws":13,"losses":12,"wins":9},"google/gemini-3.8-flash":{"draws":5,"losses":7,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":6,"wins":4},"gpt-4.1":{"draws":7,"losses":8,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":11,"wins":3},"gpt-5.4":{"draws":2,"losses":10,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":6,"wins":7},"gpt-5.4-nano":{"draws":7,"losses":20,"wins":19},"gpt-5.5":{"draws":14,"losses":11,"wins":1},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":2,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":8,"wins":1},"gpt-6-astra":{"draws":0,"losses":8,"wins":0},"gpt-6-luna":{"draws":2,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":5,"wins":7},"inclusionai/ling-3.0-flash":{"draws":14,"losses":8,"wins":18},"meituan/longcat-2.0":{"draws":14,"losses":12,"wins":12},"meta/muse-glimmer-30b":{"draws":2,"losses":4,"wins":4},"meta/muse-spark-1.2":{"draws":7,"losses":12,"wins":1},"meta/muse-spark-1.3":{"draws":2,"losses":10,"wins":0},"minimax/minimax-m3":{"draws":8,"losses":16,"wins":4},"mistralai/mistral-medium-3-5":{"draws":0,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":16,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":24,"wins":0},"nex-agi/nex-n2-pro":{"draws":4,"losses":12,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":2,"wins":13},"o3":{"draws":8,"losses":11,"wins":5},"openai/gpt-oss-120b":{"draws":4,"losses":6,"wins":0},"poolside/laguna-s-2.1":{"draws":6,"losses":17,"wins":11},"qwen/qwen3.7-max":{"draws":2,"losses":16,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":8,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":8,"wins":0},"qwen/qwen3.8-27b":{"draws":4,"losses":4,"wins":0},"qwen/qwen3.8-flash":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":1,"losses":3,"wins":2},"qwen/qwen3.8-max-0902":{"draws":4,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":5,"losses":22,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":10,"wins":4},"tencent/hy3-preview":{"draws":14,"losses":13,"wins":5},"tencent/hy4-preview":{"draws":2,"losses":8,"wins":0},"thinkingmachines/inkling":{"draws":8,"losses":18,"wins":4},"thinkingmachines/inkling-small":{"draws":3,"losses":2,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":12,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":6,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":9,"losses":10,"wins":1},"xiaomi/mimo-v2.5":{"draws":26,"losses":45,"wins":25},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":12,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":16,"losses":11,"wins":9},"z-ai/glm-5.3":{"draws":1,"losses":6,"wins":1},"z-ai/glm-5.3-flash":{"draws":2,"losses":9,"wins":1},"z-ai/glm-5.3-flashx":{"draws":2,"losses":6,"wins":0}},"gpt-4.1":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":2,"wins":2},"claude-fable-5":{"draws":0,"losses":4,"wins":4},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":35,"losses":12,"wins":11},"claude-opus-4-8":{"draws":19,"losses":24,"wins":7},"claude-opus-5":{"draws":12,"losses":70,"wins":7},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":3,"losses":3,"wins":2},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":17},"deepseek/deepseek-v4-flash":{"draws":26,"losses":7,"wins":19},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":8,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":12,"wins":5},"google/gemini-3.1-flash-lite":{"draws":14,"losses":6,"wins":18},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":4},"google/gemini-3.5-flash-lite":{"draws":15,"losses":17,"wins":12},"google/gemini-3.6-flash":{"draws":19,"losses":26,"wins":11},"google/gemini-3.8-flash":{"draws":5,"losses":6,"wins":3},"google/gemma-4-31b-it":{"draws":9,"losses":6,"wins":11},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":9,"wins":13},"gpt-5.4":{"draws":4,"losses":7,"wins":3},"gpt-5.4-mini":{"draws":20,"losses":19,"wins":5},"gpt-5.4-nano":{"draws":13,"losses":24,"wins":15},"gpt-5.5":{"draws":18,"losses":16,"wins":10},"gpt-5.6-luna":{"draws":3,"losses":0,"wins":7},"gpt-5.6-sol":{"draws":6,"losses":9,"wins":1},"gpt-5.6-terra":{"draws":10,"losses":3,"wins":3},"gpt-6-astra":{"draws":4,"losses":12,"wins":0},"gpt-6-luna":{"draws":2,"losses":2,"wins":0},"gpt-6-sol":{"draws":6,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":1,"losses":8,"wins":5},"inclusionai/ling-3.0-flash":{"draws":20,"losses":0,"wins":18},"meituan/longcat-2.0":{"draws":13,"losses":8,"wins":25},"meta/muse-glimmer-30b":{"draws":6,"losses":2,"wins":6},"meta/muse-spark-1.2":{"draws":2,"losses":11,"wins":7},"meta/muse-spark-1.3":{"draws":6,"losses":7,"wins":1},"minimax/minimax-m3":{"draws":12,"losses":9,"wins":21},"mistralai/mistral-medium-3-5":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":7,"wins":5},"moonshotai/kimi-k3":{"draws":8,"losses":11,"wins":3},"nex-agi/nex-n2-pro":{"draws":6,"losses":8,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":18,"losses":9,"wins":21},"o3":{"draws":8,"losses":14,"wins":16},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":12,"losses":10,"wins":14},"qwen/qwen3.7-max":{"draws":15,"losses":7,"wins":0},"qwen/qwen3.7-plus":{"draws":10,"losses":4,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":7,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":12,"wins":2},"qwen/qwen3.8-max":{"draws":8,"losses":3,"wins":3},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":0},"stealth/ox-alpha":{"draws":15,"losses":23,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":11},"tencent/hy3-preview":{"draws":20,"losses":6,"wins":12},"tencent/hy4-preview":{"draws":0,"losses":11,"wins":5},"thinkingmachines/inkling":{"draws":12,"losses":19,"wins":13},"thinkingmachines/inkling-small":{"draws":3,"losses":3,"wins":4},"x-ai/grok-4.5":{"draws":10,"losses":16,"wins":6},"x-ai/grok-4.6":{"draws":13,"losses":8,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":11,"losses":6,"wins":9},"xiaomi/mimo-v2.5":{"draws":40,"losses":20,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":5,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":17,"losses":27,"wins":18},"z-ai/glm-5.3":{"draws":1,"losses":7,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":5,"wins":2},"z-ai/glm-5.3-flashx":{"draws":8,"losses":8,"wins":4}},"gpt-4.1-nano":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":4},"claude-opus-4-5":{"draws":2,"losses":6,"wins":0},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":2,"losses":3,"wins":1},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":0,"losses":7,"wins":5},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":0,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":5},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":5},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":1},"google/gemini-3.5-flash":{"draws":0,"losses":4,"wins":2},"google/gemini-3.5-flash-lite":{"draws":3,"losses":14,"wins":17},"google/gemini-3.6-flash":{"draws":16,"losses":4,"wins":10},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":0,"wins":2},"gpt-5.4":{"draws":0,"losses":6,"wins":0},"gpt-5.4-nano":{"draws":3,"losses":1,"wins":2},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":0,"losses":6,"wins":2},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":7,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":2,"losses":1,"wins":11},"meituan/longcat-2.0":{"draws":1,"losses":0,"wins":3},"meta/muse-glimmer-30b":{"draws":2,"losses":1,"wins":3},"meta/muse-spark-1.2":{"draws":2,"losses":7,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":6,"losses":6,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":0,"losses":8,"wins":16},"openai/gpt-oss-120b":{"draws":0,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.8-flash":{"draws":1,"losses":5,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":2},"stealth/ox-alpha":{"draws":1,"losses":16,"wins":1},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":12},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":6,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":2,"losses":4,"wins":2},"z-ai/glm-5.3":{"draws":1,"losses":5,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.3-flashx":{"draws":0,"losses":2,"wins":0}},"gpt-5":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":7,"wins":5},"claude-fable-5":{"draws":2,"losses":13,"wins":1},"claude-fable-5-1":{"draws":0,"losses":16,"wins":0},"claude-opus-4-5":{"draws":6,"losses":7,"wins":5},"claude-opus-4-8":{"draws":0,"losses":4,"wins":2},"claude-opus-5":{"draws":8,"losses":28,"wins":2},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":2,"losses":3,"wins":1},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":4},"deepseek/deepseek-v4-flash":{"draws":9,"losses":4,"wins":5},"deepseek/deepseek-v4-pro":{"draws":6,"losses":8,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":4,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":1,"wins":3},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":5,"losses":10,"wins":7},"google/gemini-3.5-flash-lite":{"draws":11,"losses":3,"wins":8},"google/gemini-3.6-flash":{"draws":5,"losses":4,"wins":11},"google/gemini-3.8-flash":{"draws":8,"losses":4,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":1},"gpt-4.1":{"draws":2,"losses":1,"wins":3},"gpt-5":{"draws":6,"losses":6,"wins":6},"gpt-5.4":{"draws":6,"losses":3,"wins":3},"gpt-5.4-mini":{"draws":9,"losses":5,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":2,"wins":6},"gpt-5.5":{"draws":6,"losses":17,"wins":1},"gpt-5.6-luna":{"draws":2,"losses":0,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":11,"wins":3},"gpt-5.6-terra":{"draws":1,"losses":6,"wins":3},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"gpt-6-luna":{"draws":2,"losses":0,"wins":2},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":10,"losses":8,"wins":8},"meta/muse-glimmer-30b":{"draws":0,"losses":3,"wins":5},"meta/muse-spark-1.2":{"draws":4,"losses":4,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":8,"wins":1},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":4},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":3,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":4,"wins":2},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":4,"wins":7},"o3":{"draws":6,"losses":4,"wins":8},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":2},"poolside/laguna-s-2.1":{"draws":3,"losses":1,"wins":10},"qwen/qwen3.7-max":{"draws":5,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":4,"wins":6},"qwen/qwen3.8-27b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-flash":{"draws":3,"losses":1,"wins":6},"qwen/qwen3.8-max":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.8-max-0902":{"draws":0,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":10,"losses":18,"wins":4},"stepfun/step-3.7-flash":{"draws":5,"losses":3,"wins":4},"tencent/hy3-preview":{"draws":11,"losses":7,"wins":4},"tencent/hy4-preview":{"draws":7,"losses":7,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":6,"wins":8},"thinkingmachines/inkling-small":{"draws":5,"losses":1,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":6,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":2,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":13,"wins":11},"z-ai/glm-5.3":{"draws":3,"losses":6,"wins":1},"z-ai/glm-5.3-flash":{"draws":6,"losses":6,"wins":8},"z-ai/glm-5.3-flashx":{"draws":1,"losses":3,"wins":0}},"gpt-5.4":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":13,"wins":8},"claude-fable-5":{"draws":8,"losses":29,"wins":11},"claude-fable-5-1":{"draws":4,"losses":40,"wins":2},"claude-opus-4-5":{"draws":24,"losses":23,"wins":23},"claude-opus-4-8":{"draws":2,"losses":6,"wins":2},"claude-opus-5":{"draws":4,"losses":19,"wins":3},"claude-opus-5-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":32,"losses":19,"wins":41},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":7},"deepseek/deepseek-v4-flash":{"draws":23,"losses":11,"wins":16},"deepseek/deepseek-v4-pro":{"draws":16,"losses":17,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":15,"wins":15},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":6},"google/gemini-3.5-flash":{"draws":11,"losses":25,"wins":12},"google/gemini-3.5-flash-lite":{"draws":60,"losses":31,"wins":69},"google/gemini-3.6-flash":{"draws":39,"losses":58,"wins":53},"google/gemini-3.8-flash":{"draws":17,"losses":24,"wins":15},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":5,"losses":7,"wins":6},"gpt-5.4":{"draws":21,"losses":64,"wins":3},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":5,"losses":4,"wins":5},"gpt-5.5":{"draws":5,"losses":7,"wins":8},"gpt-5.6-luna":{"draws":53,"losses":24,"wins":35},"gpt-5.6-sol":{"draws":19,"losses":45,"wins":18},"gpt-5.6-terra":{"draws":18,"losses":10,"wins":8},"gpt-6-astra":{"draws":1,"losses":39,"wins":4},"gpt-6-luna":{"draws":6,"losses":2,"wins":6},"gpt-6-sol":{"draws":2,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":19,"losses":2,"wins":11},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":14},"meituan/longcat-2.0":{"draws":24,"losses":15,"wins":21},"meta/muse-glimmer-30b":{"draws":16,"losses":15,"wins":9},"meta/muse-spark-1.2":{"draws":11,"losses":40,"wins":15},"meta/muse-spark-1.3":{"draws":8,"losses":25,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":3,"wins":5},"mistralai/mistral-medium-3-5":{"draws":17,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":30,"losses":24,"wins":34},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":4},"o3":{"draws":18,"losses":29,"wins":43},"openai/gpt-oss-120b":{"draws":23,"losses":7,"wins":14},"poolside/laguna-s-2.1":{"draws":35,"losses":4,"wins":15},"qwen/qwen3.7-max":{"draws":1,"losses":3,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":3,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":22,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":9,"wins":13},"qwen/qwen3.8-flash":{"draws":12,"losses":14,"wins":4},"qwen/qwen3.8-max":{"draws":17,"losses":18,"wins":11},"qwen/qwen3.8-max-0902":{"draws":3,"losses":0,"wins":1},"stealth/ox-alpha":{"draws":55,"losses":67,"wins":40},"stepfun/step-3.7-flash":{"draws":8,"losses":4,"wins":14},"tencent/hy3-preview":{"draws":4,"losses":6,"wins":4},"tencent/hy4-preview":{"draws":11,"losses":22,"wins":9},"thinkingmachines/inkling":{"draws":19,"losses":6,"wins":27},"thinkingmachines/inkling-small":{"draws":24,"losses":5,"wins":11},"x-ai/grok-4.5":{"draws":20,"losses":30,"wins":24},"x-ai/grok-4.6":{"draws":18,"losses":22,"wins":12},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":9,"losses":2,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":3,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":1},"z-ai/glm-5.2":{"draws":24,"losses":18,"wins":18},"z-ai/glm-5.3":{"draws":13,"losses":26,"wins":13},"z-ai/glm-5.3-flash":{"draws":12,"losses":18,"wins":16},"z-ai/glm-5.3-flashx":{"draws":4,"losses":4,"wins":0}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":7,"wins":2},"claude-fable-5":{"draws":5,"losses":3,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":32,"losses":26,"wins":12},"claude-opus-4-8":{"draws":20,"losses":23,"wins":5},"claude-opus-5":{"draws":16,"losses":27,"wins":1},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":6,"losses":6,"wins":2},"cohere/north-mini-code":{"draws":14,"losses":6,"wins":8},"deepseek/deepseek-v4-flash":{"draws":27,"losses":13,"wins":6},"deepseek/deepseek-v4-pro":{"draws":3,"losses":6,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":5,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":6,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":5,"wins":19},"google/gemini-3.5-flash":{"draws":11,"losses":17,"wins":0},"google/gemini-3.5-flash-lite":{"draws":13,"losses":20,"wins":9},"google/gemini-3.6-flash":{"draws":20,"losses":23,"wins":5},"google/gemini-3.8-flash":{"draws":1,"losses":6,"wins":1},"google/gemma-4-31b-it":{"draws":5,"losses":15,"wins":4},"gpt-4.1":{"draws":10,"losses":1,"wins":9},"gpt-5":{"draws":19,"losses":14,"wins":3},"gpt-5.4":{"draws":3,"losses":7,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":12,"wins":2},"gpt-5.4-nano":{"draws":29,"losses":31,"wins":8},"gpt-5.5":{"draws":25,"losses":20,"wins":3},"gpt-5.6-luna":{"draws":4,"losses":6,"wins":0},"gpt-5.6-sol":{"draws":8,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":7,"wins":3},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":1,"losses":4,"wins":1},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":4,"losses":4,"wins":0},"inclusionai/ling-3.0-flash":{"draws":27,"losses":7,"wins":8},"meituan/longcat-2.0":{"draws":23,"losses":21,"wins":10},"meta/muse-glimmer-30b":{"draws":8,"losses":3,"wins":3},"meta/muse-spark-1.2":{"draws":0,"losses":8,"wins":0},"meta/muse-spark-1.3":{"draws":5,"losses":7,"wins":0},"minimax/minimax-m3":{"draws":6,"losses":20,"wins":6},"mistralai/mistral-medium-3-5":{"draws":5,"losses":0,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":6,"wins":0},"moonshotai/kimi-k3":{"draws":17,"losses":16,"wins":1},"nex-agi/nex-n2-pro":{"draws":17,"losses":12,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":35,"losses":14,"wins":7},"o3":{"draws":7,"losses":10,"wins":5},"openai/gpt-oss-120b":{"draws":3,"losses":6,"wins":3},"poolside/laguna-s-2.1":{"draws":24,"losses":8,"wins":4},"qwen/qwen3.7-max":{"draws":14,"losses":13,"wins":1},"qwen/qwen3.7-plus":{"draws":8,"losses":14,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":5,"wins":0},"qwen/qwen3.8-flash":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.8-max":{"draws":8,"losses":5,"wins":3},"qwen/qwen3.8-max-0902":{"draws":2,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":13,"losses":26,"wins":3},"stepfun/step-3.7-flash":{"draws":12,"losses":8,"wins":4},"tencent/hy3-preview":{"draws":11,"losses":11,"wins":4},"tencent/hy4-preview":{"draws":9,"losses":11,"wins":0},"thinkingmachines/inkling":{"draws":17,"losses":9,"wins":8},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":0},"x-ai/grok-4.5":{"draws":14,"losses":10,"wins":0},"x-ai/grok-4.6":{"draws":8,"losses":8,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":14,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":42,"losses":30,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":10,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":40,"losses":22,"wins":6},"z-ai/glm-5.3":{"draws":6,"losses":10,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":4,"wins":2},"z-ai/glm-5.3-flashx":{"draws":3,"losses":7,"wins":0}},"gpt-5.4-nano":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":8,"wins":7},"claude-fable-5":{"draws":2,"losses":16,"wins":2},"claude-fable-5-1":{"draws":0,"losses":14,"wins":0},"claude-opus-4-5":{"draws":25,"losses":55,"wins":24},"claude-opus-4-8":{"draws":21,"losses":49,"wins":14},"claude-opus-5":{"draws":16,"losses":90,"wins":2},"claude-opus-5-5":{"draws":0,"losses":18,"wins":0},"claude-sonnet-5":{"draws":5,"losses":3,"wins":4},"cohere/north-mini-code":{"draws":9,"losses":6,"wins":25},"deepseek/deepseek-v4-flash":{"draws":21,"losses":36,"wins":19},"deepseek/deepseek-v4-pro":{"draws":9,"losses":8,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":7,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":8,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":17,"wins":31},"google/gemini-3.5-flash":{"draws":11,"losses":25,"wins":4},"google/gemini-3.5-flash-lite":{"draws":30,"losses":19,"wins":19},"google/gemini-3.6-flash":{"draws":26,"losses":19,"wins":11},"google/gemini-3.8-flash":{"draws":0,"losses":14,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":13,"wins":21},"gpt-4.1":{"draws":11,"losses":8,"wins":9},"gpt-4.1-nano":{"draws":3,"losses":0,"wins":1},"gpt-5":{"draws":6,"losses":27,"wins":5},"gpt-5.4":{"draws":2,"losses":13,"wins":7},"gpt-5.4-mini":{"draws":33,"losses":9,"wins":24},"gpt-5.4-nano":{"draws":29,"losses":32,"wins":25},"gpt-5.5":{"draws":27,"losses":40,"wins":21},"gpt-5.6-luna":{"draws":8,"losses":12,"wins":4},"gpt-5.6-sol":{"draws":5,"losses":12,"wins":1},"gpt-5.6-terra":{"draws":6,"losses":9,"wins":5},"gpt-6-astra":{"draws":0,"losses":16,"wins":0},"gpt-6-luna":{"draws":2,"losses":8,"wins":0},"gpt-6-sol":{"draws":2,"losses":8,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":2,"losses":5,"wins":9},"inclusionai/ling-3.0-flash":{"draws":31,"losses":6,"wins":23},"meituan/longcat-2.0":{"draws":17,"losses":22,"wins":23},"meta/muse-glimmer-30b":{"draws":4,"losses":5,"wins":3},"meta/muse-spark-1.3":{"draws":6,"losses":14,"wins":2},"minimax/minimax-m3":{"draws":18,"losses":20,"wins":16},"mistralai/mistral-medium-3-5":{"draws":2,"losses":4,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":29,"wins":8},"nex-agi/nex-n2-pro":{"draws":14,"losses":20,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":27,"losses":9,"wins":24},"o3":{"draws":4,"losses":23,"wins":19},"openai/gpt-oss-120b":{"draws":0,"losses":7,"wins":3},"poolside/laguna-s-2.1":{"draws":30,"losses":22,"wins":18},"qwen/qwen3.7-max":{"draws":20,"losses":24,"wins":16},"qwen/qwen3.7-plus":{"draws":8,"losses":16,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":6,"wins":7},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":10,"losses":4,"wins":4},"qwen/qwen3.8-max":{"draws":6,"losses":9,"wins":3},"qwen/qwen3.8-max-0902":{"draws":3,"losses":7,"wins":2},"stealth/ox-alpha":{"draws":14,"losses":31,"wins":7},"stepfun/step-3.7-flash":{"draws":12,"losses":17,"wins":11},"tencent/hy3-preview":{"draws":14,"losses":23,"wins":5},"tencent/hy4-preview":{"draws":7,"losses":12,"wins":5},"thinkingmachines/inkling":{"draws":12,"losses":15,"wins":13},"thinkingmachines/inkling-small":{"draws":6,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":9,"losses":23,"wins":6},"x-ai/grok-4.6":{"draws":7,"losses":8,"wins":3},"x-ai/grok-4.7":{"draws":4,"losses":7,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":8,"wins":16},"xiaomi/mimo-v2.5":{"draws":31,"losses":56,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":25,"wins":7},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":5,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":33,"losses":26,"wins":19},"z-ai/glm-5.3":{"draws":4,"losses":13,"wins":9},"z-ai/glm-5.3-flash":{"draws":2,"losses":8,"wins":2},"z-ai/glm-5.3-flashx":{"draws":5,"losses":6,"wins":7}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":4},"claude-fable-5":{"draws":2,"losses":6,"wins":4},"claude-fable-5-1":{"draws":1,"losses":11,"wins":0},"claude-opus-4-5":{"draws":35,"losses":22,"wins":9},"claude-opus-4-8":{"draws":15,"losses":15,"wins":4},"claude-opus-5":{"draws":19,"losses":51,"wins":0},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":9,"losses":0,"wins":5},"cohere/north-mini-code":{"draws":11,"losses":5,"wins":6},"deepseek/deepseek-v4-flash":{"draws":16,"losses":4,"wins":4},"deepseek/deepseek-v4-pro":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":1,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":21,"losses":5,"wins":6},"google/gemini-3.6-flash":{"draws":20,"losses":19,"wins":9},"google/gemini-3.8-flash":{"draws":2,"losses":2,"wins":2},"google/gemma-4-31b-it":{"draws":13,"losses":4,"wins":7},"gpt-4.1":{"draws":10,"losses":6,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":11,"losses":13,"wins":4},"gpt-5.4":{"draws":8,"losses":10,"wins":4},"gpt-5.4-mini":{"draws":20,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":19,"losses":4,"wins":19},"gpt-5.5":{"draws":17,"losses":15,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":3,"wins":6},"gpt-5.6-sol":{"draws":6,"losses":1,"wins":3},"gpt-5.6-terra":{"draws":8,"losses":2,"wins":0},"gpt-6-astra":{"draws":0,"losses":10,"wins":0},"gpt-6-luna":{"draws":8,"losses":4,"wins":2},"gpt-6-sol":{"draws":5,"losses":7,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":0,"wins":5},"inclusionai/ling-3.0-flash":{"draws":29,"losses":0,"wins":3},"meituan/longcat-2.0":{"draws":36,"losses":6,"wins":3},"meta/muse-glimmer-30b":{"draws":10,"losses":2,"wins":4},"meta/muse-spark-1.2":{"draws":4,"losses":8,"wins":2},"meta/muse-spark-1.3":{"draws":3,"losses":3,"wins":2},"minimax/minimax-m3":{"draws":4,"losses":7,"wins":13},"mistralai/mistral-medium-3-5":{"draws":5,"losses":0,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":9,"losses":11,"wins":4},"nex-agi/nex-n2-pro":{"draws":9,"losses":2,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":4,"wins":8},"o3":{"draws":16,"losses":4,"wins":6},"openai/gpt-oss-120b":{"draws":9,"losses":0,"wins":5},"poolside/laguna-s-2.1":{"draws":20,"losses":11,"wins":3},"qwen/qwen3.7-max":{"draws":14,"losses":9,"wins":3},"qwen/qwen3.7-plus":{"draws":13,"losses":2,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-27b":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-max":{"draws":3,"losses":7,"wins":2},"qwen/qwen3.8-max-0902":{"draws":8,"losses":7,"wins":1},"stealth/ox-alpha":{"draws":6,"losses":16,"wins":4},"stepfun/step-3.7-flash":{"draws":6,"losses":9,"wins":5},"tencent/hy3-preview":{"draws":16,"losses":9,"wins":7},"tencent/hy4-preview":{"draws":6,"losses":4,"wins":0},"thinkingmachines/inkling":{"draws":14,"losses":3,"wins":15},"thinkingmachines/inkling-small":{"draws":4,"losses":1,"wins":7},"x-ai/grok-4.5":{"draws":10,"losses":11,"wins":1},"x-ai/grok-4.6":{"draws":8,"losses":1,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":11,"losses":1,"wins":0},"xiaomi/mimo-v2.5":{"draws":53,"losses":9,"wins":30},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":9,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":3,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":0},"z-ai/glm-5.2":{"draws":28,"losses":17,"wins":17},"z-ai/glm-5.3":{"draws":3,"losses":6,"wins":1},"z-ai/glm-5.3-flash":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.3-flashx":{"draws":10,"losses":3,"wins":3}},"gpt-5.6-luna":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":26,"wins":11},"claude-fable-5":{"draws":7,"losses":8,"wins":3},"claude-fable-5-1":{"draws":1,"losses":11,"wins":0},"claude-opus-4-5":{"draws":25,"losses":41,"wins":6},"claude-opus-4-8":{"draws":1,"losses":9,"wins":0},"claude-opus-5":{"draws":3,"losses":16,"wins":1},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":33,"losses":57,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":4,"wins":4},"deepseek/deepseek-v4-flash":{"draws":24,"losses":27,"wins":7},"deepseek/deepseek-v4-pro":{"draws":15,"losses":23,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":15,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":11,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":4,"wins":1},"google/gemini-3.5-flash":{"draws":9,"losses":19,"wins":4},"google/gemini-3.5-flash-lite":{"draws":43,"losses":93,"wins":42},"google/gemini-3.6-flash":{"draws":46,"losses":92,"wins":12},"google/gemini-3.8-flash":{"draws":5,"losses":20,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":0},"gpt-4.1":{"draws":0,"losses":6,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":2,"losses":3,"wins":1},"gpt-5.4":{"draws":31,"losses":49,"wins":8},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":6,"losses":10,"wins":2},"gpt-5.5":{"draws":4,"losses":15,"wins":1},"gpt-5.6-luna":{"draws":32,"losses":30,"wins":4},"gpt-5.6-sol":{"draws":6,"losses":66,"wins":6},"gpt-5.6-terra":{"draws":14,"losses":21,"wins":11},"gpt-6-astra":{"draws":0,"losses":16,"wins":0},"gpt-6-luna":{"draws":5,"losses":6,"wins":1},"gpt-6-sol":{"draws":4,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":19,"losses":16,"wins":7},"inclusionai/ling-3.0-flash":{"draws":18,"losses":12,"wins":4},"meituan/longcat-2.0":{"draws":20,"losses":32,"wins":14},"meta/muse-glimmer-30b":{"draws":20,"losses":30,"wins":4},"meta/muse-spark-1.2":{"draws":19,"losses":43,"wins":10},"meta/muse-spark-1.3":{"draws":5,"losses":17,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":15,"losses":11,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":25,"losses":42,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":5,"wins":3},"o3":{"draws":6,"losses":74,"wins":16},"openai/gpt-oss-120b":{"draws":26,"losses":16,"wins":8},"poolside/laguna-s-2.1":{"draws":23,"losses":27,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":7,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":23,"wins":0},"qwen/qwen3.8-27b":{"draws":6,"losses":16,"wins":4},"qwen/qwen3.8-flash":{"draws":15,"losses":12,"wins":5},"qwen/qwen3.8-max":{"draws":16,"losses":25,"wins":5},"qwen/qwen3.8-max-0902":{"draws":6,"losses":12,"wins":0},"stealth/ox-alpha":{"draws":46,"losses":56,"wins":6},"stepfun/step-3.7-flash":{"draws":5,"losses":15,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy4-preview":{"draws":10,"losses":23,"wins":5},"thinkingmachines/inkling":{"draws":22,"losses":25,"wins":19},"thinkingmachines/inkling-small":{"draws":19,"losses":30,"wins":9},"x-ai/grok-4.5":{"draws":21,"losses":44,"wins":5},"x-ai/grok-4.6":{"draws":11,"losses":21,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":30,"wins":7},"z-ai/glm-5.3":{"draws":9,"losses":14,"wins":1},"z-ai/glm-5.3-flash":{"draws":8,"losses":13,"wins":5},"z-ai/glm-5.3-flashx":{"draws":1,"losses":11,"wins":0}},"gpt-5.6-sol":{"bytedance-seed/seed-2.0-code":{"draws":12,"losses":3,"wins":25},"claude-fable-5":{"draws":8,"losses":36,"wins":16},"claude-fable-5-1":{"draws":3,"losses":56,"wins":5},"claude-opus-4-5":{"draws":19,"losses":17,"wins":50},"claude-opus-4-8":{"draws":13,"losses":6,"wins":3},"claude-opus-5":{"draws":0,"losses":22,"wins":2},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":35,"losses":19,"wins":60},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":1},"deepseek/deepseek-v4-flash":{"draws":12,"losses":12,"wins":34},"deepseek/deepseek-v4-pro":{"draws":12,"losses":19,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":19,"wins":21},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":12,"losses":22,"wins":30},"google/gemini-3.5-flash-lite":{"draws":45,"losses":20,"wins":109},"google/gemini-3.6-flash":{"draws":32,"losses":61,"wins":75},"google/gemini-3.8-flash":{"draws":9,"losses":24,"wins":17},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":4,"losses":1,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":3,"wins":7},"gpt-5.4":{"draws":34,"losses":46,"wins":26},"gpt-5.4-mini":{"draws":7,"losses":3,"wins":4},"gpt-5.4-nano":{"draws":4,"losses":2,"wins":10},"gpt-5.5":{"draws":9,"losses":7,"wins":2},"gpt-5.6-luna":{"draws":28,"losses":19,"wins":51},"gpt-5.6-sol":{"draws":10,"losses":45,"wins":21},"gpt-5.6-terra":{"draws":23,"losses":12,"wins":17},"gpt-6-astra":{"draws":2,"losses":53,"wins":5},"gpt-6-luna":{"draws":1,"losses":3,"wins":6},"gpt-6-sol":{"draws":1,"losses":6,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":0,"wins":16},"inclusionai/ling-3.0-flash":{"draws":10,"losses":2,"wins":16},"meituan/longcat-2.0":{"draws":13,"losses":4,"wins":47},"meta/muse-glimmer-30b":{"draws":12,"losses":5,"wins":17},"meta/muse-spark-1.2":{"draws":12,"losses":23,"wins":35},"meta/muse-spark-1.3":{"draws":14,"losses":23,"wins":15},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":9,"losses":2,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":28,"losses":22,"wins":38},"nex-agi/nex-n2-pro":{"draws":3,"losses":0,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":4,"wins":4},"o3":{"draws":4,"losses":26,"wins":76},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":32},"poolside/laguna-s-2.1":{"draws":21,"losses":1,"wins":36},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":26,"wins":18},"qwen/qwen3.8-27b":{"draws":7,"losses":7,"wins":14},"qwen/qwen3.8-flash":{"draws":15,"losses":12,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":16,"wins":19},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":36,"losses":77,"wins":66},"stepfun/step-3.7-flash":{"draws":0,"losses":10,"wins":16},"tencent/hy3-preview":{"draws":2,"losses":1,"wins":7},"tencent/hy4-preview":{"draws":15,"losses":24,"wins":25},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":43},"thinkingmachines/inkling-small":{"draws":13,"losses":5,"wins":27},"x-ai/grok-4.5":{"draws":11,"losses":43,"wins":32},"x-ai/grok-4.6":{"draws":16,"losses":27,"wins":19},"x-ai/grok-4.7":{"draws":2,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":3,"losses":1,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":8,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":1,"wins":0},"z-ai/glm-5.2":{"draws":9,"losses":20,"wins":33},"z-ai/glm-5.3":{"draws":7,"losses":33,"wins":16},"z-ai/glm-5.3-flash":{"draws":11,"losses":26,"wins":23},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":0}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":9,"wins":20},"claude-fable-5":{"draws":12,"losses":31,"wins":1},"claude-fable-5-1":{"draws":6,"losses":40,"wins":0},"claude-opus-4-5":{"draws":18,"losses":19,"wins":3},"claude-opus-4-8":{"draws":0,"losses":9,"wins":1},"claude-opus-5":{"draws":7,"losses":8,"wins":1},"claude-opus-5-5":{"draws":2,"losses":6,"wins":0},"claude-sonnet-5":{"draws":21,"losses":13,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":18,"losses":13,"wins":23},"deepseek/deepseek-v4-pro":{"draws":17,"losses":18,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":14,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":4,"wins":0},"google/gemini-3.1-flash-lite":{"draws":5,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":22,"losses":17,"wins":1},"google/gemini-3.5-flash-lite":{"draws":28,"losses":23,"wins":23},"google/gemini-3.6-flash":{"draws":25,"losses":20,"wins":15},"google/gemini-3.8-flash":{"draws":22,"losses":21,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":1,"wins":5},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":1},"gpt-5":{"draws":2,"losses":5,"wins":1},"gpt-5.4":{"draws":15,"losses":18,"wins":7},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":5,"wins":3},"gpt-5.5":{"draws":6,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":19,"losses":19,"wins":12},"gpt-5.6-sol":{"draws":17,"losses":26,"wins":5},"gpt-5.6-terra":{"draws":13,"losses":5,"wins":10},"gpt-6-astra":{"draws":3,"losses":31,"wins":2},"gpt-6-sol":{"draws":0,"losses":1,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":17,"losses":5,"wins":16},"inclusionai/ling-3.0-flash":{"draws":8,"losses":3,"wins":11},"meituan/longcat-2.0":{"draws":16,"losses":6,"wins":6},"meta/muse-glimmer-30b":{"draws":23,"losses":5,"wins":16},"meta/muse-spark-1.2":{"draws":18,"losses":13,"wins":9},"meta/muse-spark-1.3":{"draws":9,"losses":22,"wins":7},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":11,"losses":1,"wins":14},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":18,"losses":20,"wins":4},"nex-agi/nex-n2-pro":{"draws":4,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":0,"wins":5},"o3":{"draws":12,"losses":22,"wins":14},"openai/gpt-oss-120b":{"draws":22,"losses":1,"wins":15},"poolside/laguna-s-2.1":{"draws":25,"losses":3,"wins":4},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":14,"wins":10},"qwen/qwen3.8-27b":{"draws":11,"losses":15,"wins":2},"qwen/qwen3.8-flash":{"draws":11,"losses":5,"wins":6},"qwen/qwen3.8-max":{"draws":22,"losses":10,"wins":12},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":58,"losses":49,"wins":27},"stepfun/step-3.7-flash":{"draws":8,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":4,"losses":1,"wins":1},"tencent/hy4-preview":{"draws":15,"losses":17,"wins":8},"thinkingmachines/inkling":{"draws":10,"losses":6,"wins":10},"thinkingmachines/inkling-small":{"draws":17,"losses":10,"wins":15},"x-ai/grok-4.5":{"draws":9,"losses":20,"wins":3},"x-ai/grok-4.6":{"draws":18,"losses":26,"wins":4},"x-ai/grok-4.7":{"draws":1,"losses":4,"wins":1},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":10,"losses":1,"wins":9},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":4,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":35,"losses":11,"wins":16},"z-ai/glm-5.3":{"draws":12,"losses":19,"wins":1},"z-ai/glm-5.3-flash":{"draws":19,"losses":20,"wins":5},"z-ai/glm-5.3-flashx":{"draws":2,"losses":2,"wins":2}},"gpt-6-astra":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":6,"wins":15},"claude-fable-5":{"draws":5,"losses":13,"wins":36},"claude-fable-5-1":{"draws":7,"losses":27,"wins":30},"claude-opus-4-5":{"draws":7,"losses":7,"wins":44},"claude-opus-4-8":{"draws":5,"losses":1,"wins":14},"claude-opus-5":{"draws":4,"losses":10,"wins":12},"claude-opus-5-5":{"draws":2,"losses":4,"wins":2},"claude-sonnet-5":{"draws":5,"losses":8,"wins":33},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":3,"losses":2,"wins":37},"deepseek/deepseek-v4-pro":{"draws":1,"losses":6,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":0,"wins":36},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":1,"wins":10},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":12,"losses":1,"wins":35},"google/gemini-3.5-flash-lite":{"draws":6,"losses":1,"wins":59},"google/gemini-3.6-flash":{"draws":13,"losses":5,"wins":52},"google/gemini-3.8-flash":{"draws":7,"losses":7,"wins":38},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-4.1":{"draws":4,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":0,"wins":4},"gpt-5.4":{"draws":7,"losses":6,"wins":29},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":7},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":16},"gpt-5.5":{"draws":1,"losses":0,"wins":5},"gpt-5.6-luna":{"draws":8,"losses":0,"wins":24},"gpt-5.6-sol":{"draws":7,"losses":4,"wins":51},"gpt-5.6-terra":{"draws":9,"losses":4,"wins":35},"gpt-6-astra":{"draws":4,"losses":19,"wins":15},"gpt-6-luna":{"draws":2,"losses":1,"wins":7},"gpt-6-sol":{"draws":1,"losses":3,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":1,"losses":0,"wins":13},"meituan/longcat-2.0":{"draws":3,"losses":2,"wins":13},"meta/muse-glimmer-30b":{"draws":1,"losses":0,"wins":23},"meta/muse-spark-1.2":{"draws":5,"losses":2,"wins":25},"meta/muse-spark-1.3":{"draws":7,"losses":8,"wins":25},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":1,"losses":0,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":8,"losses":5,"wins":29},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":7},"o3":{"draws":1,"losses":0,"wins":37},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":15},"poolside/laguna-s-2.1":{"draws":12,"losses":0,"wins":12},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":5},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":4,"wins":34},"qwen/qwen3.8-27b":{"draws":0,"losses":0,"wins":28},"qwen/qwen3.8-flash":{"draws":8,"losses":0,"wins":16},"qwen/qwen3.8-max":{"draws":11,"losses":4,"wins":33},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":4},"stealth/ox-alpha":{"draws":28,"losses":17,"wins":121},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":3},"tencent/hy4-preview":{"draws":8,"losses":4,"wins":34},"thinkingmachines/inkling":{"draws":4,"losses":0,"wins":24},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":33},"x-ai/grok-4.5":{"draws":5,"losses":8,"wins":23},"x-ai/grok-4.6":{"draws":6,"losses":8,"wins":42},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":7},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":6,"losses":2,"wins":32},"z-ai/glm-5.3":{"draws":10,"losses":5,"wins":31},"z-ai/glm-5.3-flash":{"draws":10,"losses":6,"wins":38},"z-ai/glm-5.3-flashx":{"draws":2,"losses":1,"wins":7}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":5,"wins":1},"claude-fable-5":{"draws":1,"losses":3,"wins":0},"claude-fable-5-1":{"draws":0,"losses":6,"wins":0},"claude-opus-4-5":{"draws":11,"losses":8,"wins":1},"claude-opus-5":{"draws":2,"losses":8,"wins":0},"claude-opus-5-5":{"draws":3,"losses":43,"wins":0},"claude-sonnet-5":{"draws":1,"losses":4,"wins":1},"deepseek/deepseek-v4-flash":{"draws":4,"losses":3,"wins":5},"deepseek/deepseek-v4-pro":{"draws":4,"losses":0,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":6},"google/gemini-3.5-flash-lite":{"draws":2,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":8,"losses":7,"wins":1},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":2},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":2,"wins":0},"gpt-5.4":{"draws":5,"losses":9,"wins":0},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":1},"gpt-5.4-nano":{"draws":3,"losses":3,"wins":0},"gpt-5.5":{"draws":3,"losses":2,"wins":3},"gpt-5.6-luna":{"draws":3,"losses":2,"wins":3},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":4,"wins":1},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"gpt-6-luna":{"draws":8,"losses":14,"wins":6},"gpt-6-sol":{"draws":5,"losses":34,"wins":3},"inception/mercury-2.5-preview":{"draws":2,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":5,"losses":0,"wins":1},"meituan/longcat-2.0":{"draws":3,"losses":0,"wins":1},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":1},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":5,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":4,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":0},"o3":{"draws":4,"losses":1,"wins":3},"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":2,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":1,"losses":3,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":6,"wins":0},"qwen/qwen3.8-flash":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":7,"losses":9,"wins":2},"qwen/qwen3.8-max-0902":{"draws":8,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":7,"losses":9,"wins":2},"stepfun/step-3.7-flash":{"draws":1,"losses":3,"wins":0},"tencent/hy3-preview":{"draws":7,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":0},"thinkingmachines/inkling":{"draws":4,"losses":2,"wins":0},"thinkingmachines/inkling-small":{"draws":1,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":0,"losses":3,"wins":1},"x-ai/grok-4.6":{"draws":3,"losses":2,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":20,"wins":4},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":0},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":10,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":12,"wins":3},"z-ai/glm-5.2":{"draws":2,"losses":10,"wins":6},"z-ai/glm-5.3":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.3-flashx":{"draws":13,"losses":18,"wins":5}},"gpt-6-sol":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":1,"wins":3},"claude-fable-5":{"draws":3,"losses":0,"wins":5},"claude-fable-5-1":{"draws":0,"losses":4,"wins":0},"claude-opus-4-5":{"draws":1,"losses":5,"wins":8},"claude-opus-4-8":{"draws":1,"losses":1,"wins":0},"claude-opus-5":{"draws":4,"losses":13,"wins":3},"claude-opus-5-5":{"draws":2,"losses":42,"wins":8},"claude-sonnet-5":{"draws":0,"losses":2,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":7},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":2,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":2,"wins":5},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":7},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":5},"google/gemini-3.5-flash-lite":{"draws":2,"losses":3,"wins":15},"google/gemini-3.6-flash":{"draws":4,"losses":9,"wins":13},"google/gemini-3.8-flash":{"draws":1,"losses":0,"wins":3},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":2},"gpt-4.1":{"draws":3,"losses":0,"wins":1},"gpt-5.4":{"draws":0,"losses":5,"wins":11},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":6},"gpt-5.5":{"draws":3,"losses":1,"wins":10},"gpt-5.6-luna":{"draws":4,"losses":1,"wins":1},"gpt-5.6-sol":{"draws":0,"losses":6,"wins":6},"gpt-5.6-terra":{"draws":2,"losses":2,"wins":6},"gpt-6-astra":{"draws":0,"losses":4,"wins":0},"gpt-6-luna":{"draws":9,"losses":4,"wins":33},"gpt-6-sol":{"draws":5,"losses":21,"wins":6},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":6},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":1},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":7},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":7},"meta/muse-spark-1.2":{"draws":2,"losses":2,"wins":4},"meta/muse-spark-1.3":{"draws":2,"losses":1,"wins":7},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":3},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":0,"losses":1,"wins":1},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":0,"wins":5},"o3":{"draws":2,"losses":1,"wins":7},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":6},"poolside/laguna-s-2.1":{"draws":4,"losses":0,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.8-flash":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-max-0902":{"draws":6,"losses":3,"wins":11},"stealth/ox-alpha":{"draws":6,"losses":4,"wins":14},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":0,"wins":5},"tencent/hy4-preview":{"draws":0,"losses":7,"wins":3},"thinkingmachines/inkling":{"draws":1,"losses":1,"wins":6},"thinkingmachines/inkling-small":{"draws":5,"losses":1,"wins":4},"x-ai/grok-4.5":{"draws":1,"losses":5,"wins":2},"x-ai/grok-4.6":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.7":{"draws":4,"losses":16,"wins":10},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":3},"xiaomi/mimo-v2.5":{"draws":2,"losses":1,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":3,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":3,"wins":13},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":6},"z-ai/glm-5.3":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.3-flash":{"draws":2,"losses":4,"wins":4},"z-ai/glm-5.3-flashx":{"draws":7,"losses":15,"wins":16}},"inception/mercury-2.5-preview":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":10,"wins":9},"claude-fable-5":{"draws":9,"losses":10,"wins":3},"claude-fable-5-1":{"draws":2,"losses":18,"wins":0},"claude-opus-4-5":{"draws":11,"losses":11,"wins":6},"claude-opus-4-8":{"draws":2,"losses":0,"wins":4},"claude-opus-5":{"draws":4,"losses":2,"wins":0},"claude-opus-5-5":{"draws":2,"losses":6,"wins":0},"claude-sonnet-5":{"draws":16,"losses":12,"wins":6},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":15,"losses":16,"wins":9},"deepseek/deepseek-v4-pro":{"draws":13,"losses":10,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":14,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":10,"losses":10,"wins":4},"google/gemini-3.5-flash-lite":{"draws":22,"losses":16,"wins":20},"google/gemini-3.6-flash":{"draws":17,"losses":21,"wins":8},"google/gemini-3.8-flash":{"draws":12,"losses":11,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":0,"losses":0,"wins":6},"gpt-5":{"draws":6,"losses":4,"wins":2},"gpt-5.4":{"draws":14,"losses":8,"wins":2},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":4},"gpt-5.5":{"draws":0,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":13,"losses":13,"wins":8},"gpt-5.6-sol":{"draws":9,"losses":14,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":9,"wins":7},"gpt-6-astra":{"draws":3,"losses":11,"wins":0},"gpt-6-luna":{"draws":3,"losses":5,"wins":2},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":4},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":5},"meta/muse-glimmer-30b":{"draws":13,"losses":4,"wins":11},"meta/muse-spark-1.2":{"draws":7,"losses":7,"wins":4},"meta/muse-spark-1.3":{"draws":8,"losses":9,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":7,"losses":3,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":13,"losses":12,"wins":3},"nex-agi/nex-n2-pro":{"draws":5,"losses":0,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":2,"wins":0},"o3":{"draws":4,"losses":12,"wins":10},"openai/gpt-oss-120b":{"draws":16,"losses":7,"wins":9},"poolside/laguna-s-2.1":{"draws":6,"losses":6,"wins":8},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":18,"wins":1},"qwen/qwen3.8-27b":{"draws":2,"losses":13,"wins":1},"qwen/qwen3.8-flash":{"draws":10,"losses":10,"wins":2},"qwen/qwen3.8-max":{"draws":15,"losses":14,"wins":5},"qwen/qwen3.8-max-0902":{"draws":0,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":43,"losses":45,"wins":21},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":3},"tencent/hy4-preview":{"draws":16,"losses":13,"wins":3},"thinkingmachines/inkling":{"draws":12,"losses":3,"wins":7},"thinkingmachines/inkling-small":{"draws":24,"losses":6,"wins":14},"x-ai/grok-4.5":{"draws":13,"losses":12,"wins":3},"x-ai/grok-4.6":{"draws":15,"losses":11,"wins":6},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"xiaomi/mimo-v2.5":{"draws":5,"losses":1,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":17,"losses":14,"wins":9},"z-ai/glm-5.3":{"draws":6,"losses":12,"wins":2},"z-ai/glm-5.3-flash":{"draws":12,"losses":8,"wins":6},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":0}},"inclusionai/ling-3.0-flash":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":7,"wins":2},"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-fable-5-1":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":28,"losses":21,"wins":7},"claude-opus-4-8":{"draws":25,"losses":23,"wins":0},"claude-opus-5":{"draws":17,"losses":47,"wins":4},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":7,"losses":14,"wins":3},"cohere/north-mini-code":{"draws":26,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":34,"losses":26,"wins":12},"deepseek/deepseek-v4-pro":{"draws":10,"losses":8,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":16,"wins":2},"google/gemini-3.1-flash-lite":{"draws":14,"losses":23,"wins":11},"google/gemini-3.5-flash":{"draws":11,"losses":9,"wins":0},"google/gemini-3.5-flash-lite":{"draws":42,"losses":28,"wins":8},"google/gemini-3.6-flash":{"draws":59,"losses":40,"wins":11},"google/gemini-3.8-flash":{"draws":11,"losses":13,"wins":0},"google/gemma-4-31b-it":{"draws":14,"losses":20,"wins":6},"gpt-4.1":{"draws":16,"losses":18,"wins":0},"gpt-4.1-nano":{"draws":2,"losses":3,"wins":1},"gpt-5":{"draws":15,"losses":11,"wins":22},"gpt-5.4":{"draws":4,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":32,"losses":15,"wins":7},"gpt-5.4-nano":{"draws":42,"losses":25,"wins":11},"gpt-5.5":{"draws":43,"losses":22,"wins":3},"gpt-5.6-luna":{"draws":14,"losses":10,"wins":0},"gpt-5.6-sol":{"draws":1,"losses":13,"wins":0},"gpt-5.6-terra":{"draws":7,"losses":13,"wins":0},"gpt-6-astra":{"draws":1,"losses":7,"wins":0},"gpt-6-luna":{"draws":5,"losses":5,"wins":2},"gpt-6-sol":{"draws":0,"losses":7,"wins":3},"inception/mercury-2.5-preview":{"draws":5,"losses":3,"wins":2},"inclusionai/ling-3.0-flash":{"draws":26,"losses":18,"wins":18},"meituan/longcat-2.0":{"draws":58,"losses":33,"wins":17},"meta/muse-glimmer-30b":{"draws":10,"losses":6,"wins":2},"meta/muse-spark-1.2":{"draws":5,"losses":4,"wins":1},"meta/muse-spark-1.3":{"draws":5,"losses":10,"wins":3},"minimax/minimax-m3":{"draws":25,"losses":23,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":9,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":25,"losses":9,"wins":0},"nex-agi/nex-n2-pro":{"draws":30,"losses":18,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":21,"wins":9},"o3":{"draws":16,"losses":13,"wins":5},"openai/gpt-oss-120b":{"draws":3,"losses":12,"wins":1},"poolside/laguna-s-2.1":{"draws":62,"losses":26,"wins":12},"qwen/qwen3.7-max":{"draws":24,"losses":9,"wins":7},"qwen/qwen3.7-plus":{"draws":22,"losses":10,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":21,"wins":0},"qwen/qwen3.8-27b":{"draws":9,"losses":10,"wins":3},"qwen/qwen3.8-flash":{"draws":9,"losses":14,"wins":1},"qwen/qwen3.8-max":{"draws":9,"losses":11,"wins":0},"qwen/qwen3.8-max-0902":{"draws":10,"losses":19,"wins":1},"stealth/ox-alpha":{"draws":19,"losses":25,"wins":2},"stepfun/step-3.7-flash":{"draws":20,"losses":12,"wins":2},"tencent/hy3-preview":{"draws":13,"losses":19,"wins":4},"tencent/hy4-preview":{"draws":4,"losses":6,"wins":2},"thinkingmachines/inkling":{"draws":31,"losses":28,"wins":21},"thinkingmachines/inkling-small":{"draws":10,"losses":5,"wins":1},"x-ai/grok-4.5":{"draws":15,"losses":37,"wins":6},"x-ai/grok-4.6":{"draws":9,"losses":5,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":4,"wins":1},"x-ai/grok-build-0.1":{"draws":12,"losses":12,"wins":0},"xiaomi/mimo-v2.5":{"draws":54,"losses":37,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":17,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":6,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":49,"losses":15,"wins":6},"z-ai/glm-5.3":{"draws":7,"losses":11,"wins":0},"z-ai/glm-5.3-flash":{"draws":6,"losses":6,"wins":4},"z-ai/glm-5.3-flashx":{"draws":7,"losses":11,"wins":2}},"meituan/longcat-2.0":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":6,"wins":5},"claude-fable-5":{"draws":1,"losses":14,"wins":5},"claude-fable-5-1":{"draws":0,"losses":13,"wins":1},"claude-opus-4-5":{"draws":37,"losses":43,"wins":18},"claude-opus-4-8":{"draws":7,"losses":21,"wins":12},"claude-opus-5":{"draws":10,"losses":100,"wins":10},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":9,"losses":11,"wins":4},"cohere/north-mini-code":{"draws":31,"losses":3,"wins":16},"deepseek/deepseek-v4-flash":{"draws":24,"losses":21,"wins":23},"deepseek/deepseek-v4-pro":{"draws":4,"losses":14,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":6,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":9,"wins":5},"google/gemini-3.1-flash-lite":{"draws":13,"losses":21,"wins":30},"google/gemini-3.5-flash":{"draws":9,"losses":22,"wins":11},"google/gemini-3.5-flash-lite":{"draws":34,"losses":47,"wins":15},"google/gemini-3.6-flash":{"draws":39,"losses":37,"wins":28},"google/gemini-3.8-flash":{"draws":6,"losses":18,"wins":0},"google/gemma-4-31b-it":{"draws":14,"losses":17,"wins":19},"gpt-4.1":{"draws":10,"losses":18,"wins":6},"gpt-4.1-nano":{"draws":1,"losses":3,"wins":0},"gpt-5":{"draws":27,"losses":35,"wins":20},"gpt-5.4":{"draws":13,"losses":13,"wins":4},"gpt-5.4-mini":{"draws":28,"losses":21,"wins":21},"gpt-5.4-nano":{"draws":25,"losses":52,"wins":35},"gpt-5.5":{"draws":40,"losses":17,"wins":17},"gpt-5.6-luna":{"draws":6,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":2,"losses":26,"wins":0},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":2},"gpt-6-astra":{"draws":2,"losses":18,"wins":0},"gpt-6-luna":{"draws":2,"losses":3,"wins":1},"gpt-6-sol":{"draws":2,"losses":17,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":8,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":50,"losses":24,"wins":32},"meituan/longcat-2.0":{"draws":17,"losses":25,"wins":25},"meta/muse-glimmer-30b":{"draws":10,"losses":4,"wins":6},"meta/muse-spark-1.2":{"draws":8,"losses":9,"wins":5},"meta/muse-spark-1.3":{"draws":6,"losses":24,"wins":4},"minimax/minimax-m3":{"draws":13,"losses":16,"wins":15},"mistralai/mistral-medium-3-5":{"draws":7,"losses":8,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":8,"wins":2},"moonshotai/kimi-k3":{"draws":25,"losses":20,"wins":13},"nex-agi/nex-n2-pro":{"draws":13,"losses":12,"wins":21},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":19,"wins":13},"o3":{"draws":17,"losses":14,"wins":25},"openai/gpt-oss-120b":{"draws":8,"losses":13,"wins":9},"poolside/laguna-s-2.1":{"draws":52,"losses":43,"wins":25},"qwen/qwen3.7-max":{"draws":25,"losses":18,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":12,"wins":13},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":11,"wins":3},"qwen/qwen3.8-27b":{"draws":8,"losses":7,"wins":1},"qwen/qwen3.8-flash":{"draws":11,"losses":3,"wins":2},"qwen/qwen3.8-max":{"draws":8,"losses":8,"wins":6},"qwen/qwen3.8-max-0902":{"draws":7,"losses":11,"wins":4},"stealth/ox-alpha":{"draws":17,"losses":61,"wins":16},"stepfun/step-3.7-flash":{"draws":10,"losses":19,"wins":17},"tencent/hy3-preview":{"draws":26,"losses":20,"wins":20},"tencent/hy4-preview":{"draws":3,"losses":10,"wins":5},"thinkingmachines/inkling":{"draws":22,"losses":37,"wins":23},"thinkingmachines/inkling-small":{"draws":11,"losses":7,"wins":6},"x-ai/grok-4.5":{"draws":18,"losses":43,"wins":17},"x-ai/grok-4.6":{"draws":9,"losses":6,"wins":3},"x-ai/grok-4.7":{"draws":0,"losses":10,"wins":0},"x-ai/grok-build-0.1":{"draws":9,"losses":10,"wins":13},"xiaomi/mimo-v2.5":{"draws":53,"losses":50,"wins":55},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":31,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":42,"losses":51,"wins":25},"z-ai/glm-5.3":{"draws":4,"losses":20,"wins":0},"z-ai/glm-5.3-flash":{"draws":14,"losses":14,"wins":6},"z-ai/glm-5.3-flashx":{"draws":9,"losses":4,"wins":3}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":20,"wins":6},"claude-fable-5":{"draws":7,"losses":11,"wins":4},"claude-fable-5-1":{"draws":2,"losses":16,"wins":0},"claude-opus-4-5":{"draws":9,"losses":19,"wins":4},"claude-opus-4-8":{"draws":4,"losses":3,"wins":1},"claude-opus-5":{"draws":0,"losses":17,"wins":1},"claude-opus-5-5":{"draws":2,"losses":6,"wins":0},"claude-sonnet-5":{"draws":10,"losses":23,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":22,"losses":17,"wins":7},"deepseek/deepseek-v4-pro":{"draws":15,"losses":12,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":19,"losses":13,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":4,"wins":2},"google/gemini-3.5-flash":{"draws":10,"losses":16,"wins":10},"google/gemini-3.5-flash-lite":{"draws":30,"losses":24,"wins":20},"google/gemini-3.6-flash":{"draws":27,"losses":30,"wins":5},"google/gemini-3.8-flash":{"draws":12,"losses":17,"wins":5},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":2,"losses":9,"wins":3},"gpt-5.4":{"draws":10,"losses":12,"wins":4},"gpt-5.4-mini":{"draws":4,"losses":4,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":4},"gpt-5.5":{"draws":6,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":18,"losses":15,"wins":11},"gpt-5.6-sol":{"draws":4,"losses":14,"wins":2},"gpt-5.6-terra":{"draws":12,"losses":16,"wins":4},"gpt-6-astra":{"draws":0,"losses":24,"wins":0},"gpt-6-luna":{"draws":1,"losses":1,"wins":0},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":13,"losses":6,"wins":7},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":7,"losses":9,"wins":10},"meta/muse-glimmer-30b":{"draws":13,"losses":10,"wins":3},"meta/muse-spark-1.2":{"draws":5,"losses":15,"wins":2},"meta/muse-spark-1.3":{"draws":9,"losses":13,"wins":4},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":10,"losses":4,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":10,"losses":17,"wins":5},"nex-agi/nex-n2-pro":{"draws":1,"losses":2,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"wins":3},"o3":{"draws":8,"losses":17,"wins":9},"openai/gpt-oss-120b":{"draws":12,"losses":13,"wins":9},"poolside/laguna-s-2.1":{"draws":9,"losses":10,"wins":5},"qwen/qwen3.7-max":{"draws":2,"losses":6,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":12,"wins":2},"qwen/qwen3.8-27b":{"draws":11,"losses":14,"wins":1},"qwen/qwen3.8-flash":{"draws":13,"losses":2,"wins":5},"qwen/qwen3.8-max":{"draws":11,"losses":10,"wins":7},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":36,"losses":64,"wins":16},"stepfun/step-3.7-flash":{"draws":4,"losses":2,"wins":2},"tencent/hy3-preview":{"draws":0,"losses":4,"wins":0},"tencent/hy4-preview":{"draws":16,"losses":14,"wins":2},"thinkingmachines/inkling":{"draws":11,"losses":14,"wins":11},"thinkingmachines/inkling-small":{"draws":19,"losses":8,"wins":13},"x-ai/grok-4.5":{"draws":5,"losses":14,"wins":3},"x-ai/grok-4.6":{"draws":14,"losses":12,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":13,"losses":4,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":24,"losses":14,"wins":12},"z-ai/glm-5.3":{"draws":3,"losses":15,"wins":4},"z-ai/glm-5.3-flash":{"draws":14,"losses":17,"wins":1},"z-ai/glm-5.3-flashx":{"draws":2,"losses":0,"wins":0}},"meta/muse-spark-1.2":{"bytedance-seed/seed-2.0-code":{"draws":17,"losses":12,"wins":13},"claude-fable-5":{"draws":7,"losses":23,"wins":6},"claude-fable-5-1":{"draws":6,"losses":44,"wins":0},"claude-opus-4-5":{"draws":23,"losses":30,"wins":25},"claude-opus-4-8":{"draws":9,"losses":14,"wins":3},"claude-opus-5":{"draws":1,"losses":17,"wins":4},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":34,"losses":36,"wins":30},"cohere/north-mini-code":{"draws":1,"losses":6,"wins":9},"deepseek/deepseek-v4-flash":{"draws":8,"losses":15,"wins":17},"deepseek/deepseek-v4-pro":{"draws":10,"losses":20,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":18,"losses":20,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":2,"wins":4},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":10,"losses":28,"wins":8},"google/gemini-3.5-flash-lite":{"draws":48,"losses":41,"wins":69},"google/gemini-3.6-flash":{"draws":36,"losses":83,"wins":49},"google/gemini-3.8-flash":{"draws":14,"losses":18,"wins":12},"google/gemma-4-31b-it":{"draws":5,"losses":1,"wins":8},"gpt-4.1":{"draws":0,"losses":6,"wins":8},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":2},"gpt-5":{"draws":9,"losses":2,"wins":5},"gpt-5.4":{"draws":17,"losses":40,"wins":27},"gpt-5.4-mini":{"draws":2,"losses":6,"wins":6},"gpt-5.4-nano":{"draws":0,"losses":6,"wins":4},"gpt-5.5":{"draws":5,"losses":6,"wins":5},"gpt-5.6-luna":{"draws":23,"losses":32,"wins":37},"gpt-5.6-sol":{"draws":12,"losses":69,"wins":11},"gpt-5.6-terra":{"draws":11,"losses":17,"wins":18},"gpt-6-astra":{"draws":1,"losses":36,"wins":1},"gpt-6-luna":{"draws":0,"losses":0,"wins":2},"gpt-6-sol":{"draws":1,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":3},"inception/mercury-2.5-preview":{"draws":14,"losses":3,"wins":25},"inclusionai/ling-3.0-flash":{"draws":11,"losses":6,"wins":9},"meituan/longcat-2.0":{"draws":14,"losses":28,"wins":24},"meta/muse-glimmer-30b":{"draws":10,"losses":15,"wins":15},"meta/muse-spark-1.2":{"draws":9,"losses":29,"wins":6},"meta/muse-spark-1.3":{"draws":9,"losses":21,"wins":8},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":5},"mistralai/mistral-medium-3-5":{"draws":14,"losses":4,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":5,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":42,"wins":23},"nex-agi/nex-n2-pro":{"draws":5,"losses":4,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":8},"o3":{"draws":4,"losses":62,"wins":40},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":16,"losses":12,"wins":28},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":23,"wins":10},"qwen/qwen3.8-27b":{"draws":3,"losses":16,"wins":13},"qwen/qwen3.8-flash":{"draws":10,"losses":13,"wins":7},"qwen/qwen3.8-max":{"draws":14,"losses":21,"wins":15},"qwen/qwen3.8-max-0902":{"draws":3,"losses":7,"wins":2},"stealth/ox-alpha":{"draws":43,"losses":99,"wins":38},"stepfun/step-3.7-flash":{"draws":0,"losses":11,"wins":15},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":7},"tencent/hy4-preview":{"draws":11,"losses":27,"wins":16},"thinkingmachines/inkling":{"draws":30,"losses":13,"wins":33},"thinkingmachines/inkling-small":{"draws":14,"losses":16,"wins":22},"x-ai/grok-4.5":{"draws":17,"losses":45,"wins":10},"x-ai/grok-4.6":{"draws":8,"losses":33,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":3,"wins":5},"xiaomi/mimo-v2.5":{"draws":6,"losses":7,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":5,"wins":0},"z-ai/glm-5.2":{"draws":17,"losses":29,"wins":22},"z-ai/glm-5.3":{"draws":6,"losses":26,"wins":6},"z-ai/glm-5.3-flash":{"draws":9,"losses":22,"wins":9},"z-ai/glm-5.3-flashx":{"draws":1,"losses":2,"wins":5}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":10,"wins":19},"claude-fable-5":{"draws":8,"losses":21,"wins":5},"claude-fable-5-1":{"draws":0,"losses":26,"wins":0},"claude-opus-4-5":{"draws":14,"losses":18,"wins":12},"claude-opus-4-8":{"draws":1,"losses":8,"wins":1},"claude-opus-5":{"draws":4,"losses":21,"wins":1},"claude-sonnet-5":{"draws":25,"losses":18,"wins":13},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":24,"losses":15,"wins":23},"deepseek/deepseek-v4-pro":{"draws":12,"losses":20,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":16,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":15,"losses":21,"wins":12},"google/gemini-3.5-flash-lite":{"draws":32,"losses":25,"wins":39},"google/gemini-3.6-flash":{"draws":26,"losses":34,"wins":24},"google/gemini-3.8-flash":{"draws":9,"losses":18,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":4},"gpt-4.1":{"draws":5,"losses":0,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":5,"losses":4,"wins":3},"gpt-5.4":{"draws":14,"losses":22,"wins":8},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":4,"losses":4,"wins":10},"gpt-5.5":{"draws":2,"losses":4,"wins":4},"gpt-5.6-luna":{"draws":16,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":5,"losses":27,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":20,"wins":15},"gpt-6-astra":{"draws":3,"losses":21,"wins":2},"gpt-6-luna":{"draws":2,"losses":5,"wins":5},"gpt-6-sol":{"draws":0,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":7},"inception/mercury-2.5-preview":{"draws":18,"losses":3,"wins":19},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":13},"meituan/longcat-2.0":{"draws":15,"losses":6,"wins":25},"meta/muse-glimmer-30b":{"draws":29,"losses":10,"wins":11},"meta/muse-spark-1.2":{"draws":10,"losses":15,"wins":5},"meta/muse-spark-1.3":{"draws":5,"losses":14,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":19},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":18,"losses":24,"wins":12},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":3,"wins":3},"o3":{"draws":12,"losses":26,"wins":12},"openai/gpt-oss-120b":{"draws":22,"losses":9,"wins":23},"poolside/laguna-s-2.1":{"draws":10,"losses":9,"wins":9},"qwen/qwen3.7-max":{"draws":2,"losses":5,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":17,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":5},"qwen/qwen3.8-flash":{"draws":11,"losses":14,"wins":11},"qwen/qwen3.8-max":{"draws":18,"losses":8,"wins":12},"qwen/qwen3.8-max-0902":{"draws":7,"losses":3,"wins":0},"stealth/ox-alpha":{"draws":46,"losses":72,"wins":26},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":12},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":17,"losses":24,"wins":7},"thinkingmachines/inkling":{"draws":15,"losses":5,"wins":12},"thinkingmachines/inkling-small":{"draws":30,"losses":9,"wins":21},"x-ai/grok-4.5":{"draws":8,"losses":23,"wins":9},"x-ai/grok-4.6":{"draws":14,"losses":18,"wins":10},"x-ai/grok-4.7":{"draws":0,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":1,"wins":5},"xiaomi/mimo-v2.5":{"draws":12,"losses":5,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":1,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":17,"losses":18,"wins":19},"z-ai/glm-5.3":{"draws":10,"losses":27,"wins":5},"z-ai/glm-5.3-flash":{"draws":13,"losses":20,"wins":7},"z-ai/glm-5.3-flashx":{"draws":9,"losses":5,"wins":2}},"minimax/minimax-m3":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":14,"wins":4},"claude-fable-5":{"draws":3,"losses":9,"wins":2},"claude-fable-5-1":{"draws":0,"losses":7,"wins":1},"claude-opus-4-5":{"draws":13,"losses":39,"wins":10},"claude-opus-4-8":{"draws":7,"losses":27,"wins":10},"claude-opus-5":{"draws":9,"losses":55,"wins":6},"claude-opus-5-5":{"draws":2,"losses":7,"wins":1},"claude-sonnet-5":{"draws":0,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":0,"losses":8,"wins":18},"deepseek/deepseek-v4-flash":{"draws":8,"losses":7,"wins":11},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":2,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":6,"losses":6,"wins":8},"google/gemini-3.5-flash-lite":{"draws":7,"losses":6,"wins":15},"google/gemini-3.6-flash":{"draws":8,"losses":16,"wins":8},"google/gemini-3.8-flash":{"draws":0,"losses":9,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":6,"wins":10},"gpt-4.1":{"draws":4,"losses":12,"wins":8},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":1},"gpt-5":{"draws":3,"losses":13,"wins":8},"gpt-5.4":{"draws":1,"losses":5,"wins":6},"gpt-5.4-mini":{"draws":10,"losses":4,"wins":16},"gpt-5.4-nano":{"draws":14,"losses":8,"wins":20},"gpt-5.5":{"draws":8,"losses":25,"wins":7},"gpt-5.6-luna":{"draws":3,"losses":4,"wins":3},"gpt-5.6-sol":{"draws":6,"losses":6,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":2,"wins":6},"gpt-6-astra":{"draws":0,"losses":16,"wins":0},"gpt-6-luna":{"draws":4,"losses":4,"wins":0},"gpt-6-sol":{"draws":1,"losses":7,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":8,"losses":1,"wins":1},"inception/mercury-2.5-preview":{"draws":0,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":12,"losses":6,"wins":14},"meituan/longcat-2.0":{"draws":3,"losses":5,"wins":14},"meta/muse-glimmer-30b":{"draws":5,"losses":1,"wins":4},"meta/muse-spark-1.2":{"draws":2,"losses":0,"wins":0},"meta/muse-spark-1.3":{"draws":2,"losses":10,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":1,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":4,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":13,"wins":0},"nex-agi/nex-n2-pro":{"draws":7,"losses":6,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":10,"wins":19},"o3":{"draws":1,"losses":16,"wins":7},"openai/gpt-oss-120b":{"draws":2,"losses":7,"wins":3},"poolside/laguna-s-2.1":{"draws":6,"losses":9,"wins":15},"qwen/qwen3.7-max":{"draws":15,"losses":14,"wins":5},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":4,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-max":{"draws":6,"losses":5,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":1,"wins":2},"stealth/ox-alpha":{"draws":13,"losses":22,"wins":7},"stepfun/step-3.7-flash":{"draws":0,"losses":3,"wins":13},"tencent/hy3-preview":{"draws":4,"losses":13,"wins":11},"tencent/hy4-preview":{"draws":1,"losses":6,"wins":1},"thinkingmachines/inkling":{"draws":10,"losses":12,"wins":18},"thinkingmachines/inkling-small":{"draws":0,"losses":4,"wins":4},"x-ai/grok-4.5":{"draws":3,"losses":12,"wins":3},"x-ai/grok-4.6":{"draws":4,"losses":10,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":3,"wins":0},"x-ai/grok-build-0.1":{"draws":3,"losses":6,"wins":7},"xiaomi/mimo-v2.5":{"draws":16,"losses":18,"wins":26},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":12,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":1,"wins":0},"z-ai/glm-5.2":{"draws":12,"losses":4,"wins":14},"z-ai/glm-5.3":{"draws":2,"losses":7,"wins":1},"z-ai/glm-5.3-flash":{"draws":2,"losses":8,"wins":2},"z-ai/glm-5.3-flashx":{"draws":0,"losses":4,"wins":2}},"mistralai/mistral-medium-3-5":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":14,"wins":8},"claude-fable-5":{"draws":9,"losses":11,"wins":2},"claude-fable-5-1":{"draws":1,"losses":19,"wins":0},"claude-opus-4-5":{"draws":6,"losses":26,"wins":2},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":2,"losses":16,"wins":2},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":17,"losses":23,"wins":2},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":20,"losses":16,"wins":4},"deepseek/deepseek-v4-pro":{"draws":17,"losses":22,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":14,"losses":22,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":2},"google/gemini-3.5-flash":{"draws":10,"losses":19,"wins":5},"google/gemini-3.5-flash-lite":{"draws":25,"losses":40,"wins":17},"google/gemini-3.6-flash":{"draws":24,"losses":33,"wins":5},"google/gemini-3.8-flash":{"draws":10,"losses":16,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":3,"wins":1},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":7,"losses":1,"wins":4},"gpt-5.4":{"draws":11,"losses":6,"wins":7},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":1,"losses":2,"wins":5},"gpt-5.5":{"draws":2,"losses":6,"wins":0},"gpt-5.6-luna":{"draws":16,"losses":17,"wins":9},"gpt-5.6-sol":{"draws":3,"losses":19,"wins":2},"gpt-5.6-terra":{"draws":11,"losses":20,"wins":3},"gpt-6-astra":{"draws":0,"losses":8,"wins":0},"gpt-6-luna":{"draws":0,"losses":2,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":18,"losses":13,"wins":5},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":7},"meituan/longcat-2.0":{"draws":10,"losses":14,"wins":5},"meta/muse-glimmer-30b":{"draws":22,"losses":17,"wins":5},"meta/muse-spark-1.2":{"draws":10,"losses":21,"wins":3},"meta/muse-spark-1.3":{"draws":8,"losses":16,"wins":0},"mistralai/mistral-medium-3-5":{"draws":8,"losses":7,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":20,"wins":0},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":5,"wins":2},"o3":{"draws":9,"losses":23,"wins":2},"openai/gpt-oss-120b":{"draws":18,"losses":15,"wins":3},"poolside/laguna-s-2.1":{"draws":17,"losses":15,"wins":4},"qwen/qwen3.7-max":{"draws":0,"losses":3,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":32,"wins":1},"qwen/qwen3.8-27b":{"draws":5,"losses":16,"wins":1},"qwen/qwen3.8-flash":{"draws":13,"losses":15,"wins":4},"qwen/qwen3.8-max":{"draws":13,"losses":21,"wins":4},"qwen/qwen3.8-max-0902":{"draws":4,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":38,"losses":59,"wins":13},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":1,"wins":1},"tencent/hy4-preview":{"draws":13,"losses":23,"wins":2},"thinkingmachines/inkling":{"draws":11,"losses":16,"wins":3},"thinkingmachines/inkling-small":{"draws":26,"losses":15,"wins":13},"x-ai/grok-4.5":{"draws":7,"losses":15,"wins":4},"x-ai/grok-4.6":{"draws":11,"losses":13,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":4,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":6,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":24,"losses":27,"wins":3},"z-ai/glm-5.3":{"draws":7,"losses":18,"wins":1},"z-ai/glm-5.3-flash":{"draws":14,"losses":17,"wins":5},"z-ai/glm-5.3-flashx":{"draws":2,"losses":6,"wins":2}},"moonshotai/kimi-k3":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":8,"wins":21},"claude-fable-5":{"draws":7,"losses":35,"wins":12},"claude-fable-5-1":{"draws":2,"losses":50,"wins":2},"claude-opus-4-5":{"draws":30,"losses":23,"wins":47},"claude-opus-4-8":{"draws":7,"losses":8,"wins":15},"claude-opus-5":{"draws":9,"losses":44,"wins":19},"claude-opus-5-5":{"draws":0,"losses":8,"wins":2},"claude-sonnet-5":{"draws":32,"losses":21,"wins":51},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":11},"deepseek/deepseek-v4-flash":{"draws":17,"losses":20,"wins":29},"deepseek/deepseek-v4-pro":{"draws":12,"losses":14,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":14,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":10},"google/gemini-3.5-flash":{"draws":22,"losses":18,"wins":10},"google/gemini-3.5-flash-lite":{"draws":70,"losses":42,"wins":100},"google/gemini-3.6-flash":{"draws":59,"losses":84,"wins":73},"google/gemini-3.8-flash":{"draws":13,"losses":23,"wins":12},"google/gemma-4-31b-it":{"draws":9,"losses":2,"wins":19},"gpt-4.1":{"draws":1,"losses":1,"wins":6},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":2,"losses":2,"wins":8},"gpt-5.4":{"draws":11,"losses":56,"wins":35},"gpt-5.4-mini":{"draws":11,"losses":3,"wins":10},"gpt-5.4-nano":{"draws":8,"losses":4,"wins":28},"gpt-5.5":{"draws":6,"losses":4,"wins":12},"gpt-5.6-luna":{"draws":27,"losses":18,"wins":51},"gpt-5.6-sol":{"draws":18,"losses":56,"wins":24},"gpt-5.6-terra":{"draws":16,"losses":19,"wins":25},"gpt-6-astra":{"draws":8,"losses":35,"wins":7},"gpt-6-luna":{"draws":0,"losses":3,"wins":3},"gpt-6-sol":{"draws":0,"losses":2,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":20},"inclusionai/ling-3.0-flash":{"draws":25,"losses":7,"wins":18},"meituan/longcat-2.0":{"draws":28,"losses":19,"wins":45},"meta/muse-glimmer-30b":{"draws":9,"losses":6,"wins":21},"meta/muse-spark-1.2":{"draws":18,"losses":19,"wins":31},"meta/muse-spark-1.3":{"draws":11,"losses":29,"wins":18},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":14},"mistralai/mistral-medium-3-5":{"draws":5,"losses":3,"wins":22},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":36,"losses":26,"wins":18},"nex-agi/nex-n2-pro":{"draws":6,"losses":4,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":4},"o3":{"draws":19,"losses":54,"wins":51},"openai/gpt-oss-120b":{"draws":12,"losses":9,"wins":23},"poolside/laguna-s-2.1":{"draws":34,"losses":11,"wins":43},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":11},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":18,"wins":22},"qwen/qwen3.8-27b":{"draws":2,"losses":9,"wins":13},"qwen/qwen3.8-flash":{"draws":12,"losses":14,"wins":8},"qwen/qwen3.8-max":{"draws":10,"losses":19,"wins":22},"qwen/qwen3.8-max-0902":{"draws":3,"losses":7,"wins":2},"stealth/ox-alpha":{"draws":38,"losses":63,"wins":55},"stepfun/step-3.7-flash":{"draws":3,"losses":6,"wins":19},"tencent/hy3-preview":{"draws":9,"losses":1,"wins":8},"tencent/hy4-preview":{"draws":15,"losses":16,"wins":15},"thinkingmachines/inkling":{"draws":35,"losses":15,"wins":48},"thinkingmachines/inkling-small":{"draws":16,"losses":12,"wins":29},"x-ai/grok-4.5":{"draws":33,"losses":35,"wins":44},"x-ai/grok-4.6":{"draws":6,"losses":32,"wins":14},"x-ai/grok-4.7":{"draws":1,"losses":2,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":15,"losses":9,"wins":34},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":10,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":31,"losses":11,"wins":24},"z-ai/glm-5.3":{"draws":13,"losses":22,"wins":13},"z-ai/glm-5.3-flash":{"draws":13,"losses":23,"wins":8},"z-ai/glm-5.3-flashx":{"draws":3,"losses":5,"wins":2}},"nex-agi/nex-n2-pro":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":5,"wins":0},"claude-fable-5":{"draws":1,"losses":6,"wins":1},"claude-fable-5-1":{"draws":2,"losses":10,"wins":0},"claude-opus-4-5":{"draws":15,"losses":23,"wins":14},"claude-opus-4-8":{"draws":24,"losses":20,"wins":8},"claude-opus-5":{"draws":1,"losses":35,"wins":6},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":6,"losses":4,"wins":4},"cohere/north-mini-code":{"draws":8,"losses":4,"wins":18},"deepseek/deepseek-v4-flash":{"draws":17,"losses":16,"wins":9},"deepseek/deepseek-v4-pro":{"draws":6,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":6,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":14,"losses":6,"wins":12},"google/gemini-3.5-flash":{"draws":6,"losses":6,"wins":6},"google/gemini-3.5-flash-lite":{"draws":24,"losses":5,"wins":3},"google/gemini-3.6-flash":{"draws":18,"losses":23,"wins":11},"google/gemini-3.8-flash":{"draws":3,"losses":7,"wins":2},"google/gemma-4-31b-it":{"draws":8,"losses":8,"wins":8},"gpt-4.1":{"draws":6,"losses":2,"wins":8},"gpt-5":{"draws":14,"losses":4,"wins":0},"gpt-5.4":{"draws":1,"losses":4,"wins":1},"gpt-5.4-mini":{"draws":22,"losses":12,"wins":8},"gpt-5.4-nano":{"draws":20,"losses":14,"wins":14},"gpt-5.5":{"draws":16,"losses":16,"wins":4},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":12,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":8,"wins":4},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":0,"losses":2,"wins":0},"gpt-6-sol":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":6},"inclusionai/ling-3.0-flash":{"draws":29,"losses":5,"wins":10},"meituan/longcat-2.0":{"draws":12,"losses":6,"wins":6},"meta/muse-glimmer-30b":{"draws":5,"losses":4,"wins":5},"meta/muse-spark-1.2":{"draws":4,"losses":6,"wins":6},"meta/muse-spark-1.3":{"draws":4,"losses":5,"wins":1},"minimax/minimax-m3":{"draws":15,"losses":12,"wins":5},"mistralai/mistral-medium-3-5":{"draws":11,"losses":7,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":12,"wins":5},"nex-agi/nex-n2-pro":{"draws":2,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":40,"losses":16,"wins":8},"o3":{"draws":6,"losses":10,"wins":10},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":0},"poolside/laguna-s-2.1":{"draws":16,"losses":7,"wins":7},"qwen/qwen3.7-max":{"draws":15,"losses":13,"wins":4},"qwen/qwen3.7-plus":{"draws":14,"losses":5,"wins":11},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":7,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":4,"wins":4},"qwen/qwen3.8-flash":{"draws":12,"losses":9,"wins":1},"qwen/qwen3.8-max":{"draws":4,"losses":4,"wins":2},"qwen/qwen3.8-max-0902":{"draws":0,"losses":3,"wins":3},"stealth/ox-alpha":{"draws":13,"losses":17,"wins":6},"stepfun/step-3.7-flash":{"draws":13,"losses":6,"wins":7},"tencent/hy3-preview":{"draws":26,"losses":4,"wins":8},"tencent/hy4-preview":{"draws":4,"losses":8,"wins":0},"thinkingmachines/inkling":{"draws":16,"losses":9,"wins":11},"thinkingmachines/inkling-small":{"draws":6,"losses":1,"wins":1},"x-ai/grok-4.5":{"draws":11,"losses":16,"wins":1},"x-ai/grok-4.6":{"draws":4,"losses":8,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":13,"losses":3,"wins":2},"xiaomi/mimo-v2.5":{"draws":31,"losses":19,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":5,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":0,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":0,"wins":0},"z-ai/glm-5.2":{"draws":31,"losses":17,"wins":14},"z-ai/glm-5.3":{"draws":3,"losses":7,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":5,"wins":0},"z-ai/glm-5.3-flashx":{"draws":0,"losses":7,"wins":1}},"nvidia/nemotron-3-ultra-550b-a55b":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":8,"wins":2},"claude-fable-5":{"draws":2,"losses":7,"wins":3},"claude-fable-5-1":{"draws":0,"losses":14,"wins":0},"claude-opus-4-5":{"draws":11,"losses":21,"wins":10},"claude-opus-4-8":{"draws":2,"losses":17,"wins":9},"claude-opus-5":{"draws":18,"losses":37,"wins":3},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":3,"losses":6,"wins":3},"cohere/north-mini-code":{"draws":8,"losses":14,"wins":2},"deepseek/deepseek-v4-flash":{"draws":10,"losses":28,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":1},"google/gemini-3.1-flash-lite":{"draws":8,"losses":17,"wins":9},"google/gemini-3.5-flash":{"draws":5,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":12,"losses":6,"wins":4},"google/gemini-3.6-flash":{"draws":9,"losses":16,"wins":3},"google/gemini-3.8-flash":{"draws":6,"losses":4,"wins":2},"google/gemma-4-31b-it":{"draws":5,"losses":13,"wins":4},"gpt-4.1":{"draws":6,"losses":12,"wins":2},"gpt-5":{"draws":10,"losses":6,"wins":6},"gpt-5.4":{"draws":2,"losses":1,"wins":1},"gpt-5.4-mini":{"draws":17,"losses":10,"wins":11},"gpt-5.4-nano":{"draws":8,"losses":12,"wins":6},"gpt-5.5":{"draws":21,"losses":17,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":4,"wins":5},"gpt-5.6-sol":{"draws":3,"losses":7,"wins":2},"gpt-5.6-terra":{"draws":6,"losses":10,"wins":2},"gpt-6-astra":{"draws":1,"losses":9,"wins":0},"gpt-6-luna":{"draws":2,"losses":0,"wins":0},"gpt-6-sol":{"draws":2,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":14,"losses":8,"wins":10},"meituan/longcat-2.0":{"draws":11,"losses":8,"wins":3},"meta/muse-glimmer-30b":{"draws":3,"losses":5,"wins":4},"meta/muse-spark-1.2":{"draws":2,"losses":3,"wins":1},"meta/muse-spark-1.3":{"draws":3,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":16,"wins":11},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":6,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":8,"wins":0},"nex-agi/nex-n2-pro":{"draws":14,"losses":8,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":5,"wins":6},"o3":{"draws":11,"losses":11,"wins":6},"openai/gpt-oss-120b":{"draws":2,"losses":7,"wins":5},"poolside/laguna-s-2.1":{"draws":13,"losses":8,"wins":7},"qwen/qwen3.7-max":{"draws":14,"losses":13,"wins":7},"qwen/qwen3.7-plus":{"draws":7,"losses":9,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":5,"wins":3},"qwen/qwen3.8-27b":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-flash":{"draws":3,"losses":6,"wins":5},"qwen/qwen3.8-max":{"draws":0,"losses":8,"wins":4},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":1},"stealth/ox-alpha":{"draws":9,"losses":17,"wins":4},"stepfun/step-3.7-flash":{"draws":10,"losses":8,"wins":8},"tencent/hy3-preview":{"draws":10,"losses":10,"wins":10},"tencent/hy4-preview":{"draws":8,"losses":11,"wins":1},"thinkingmachines/inkling":{"draws":11,"losses":10,"wins":7},"thinkingmachines/inkling-small":{"draws":3,"losses":3,"wins":4},"x-ai/grok-4.5":{"draws":0,"losses":12,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":14,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":24,"losses":29,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":8,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":5,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":5,"wins":0},"z-ai/glm-5.2":{"draws":19,"losses":16,"wins":15},"z-ai/glm-5.3":{"draws":2,"losses":8,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.3-flashx":{"draws":0,"losses":0,"wins":2}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":5,"wins":6},"claude-fable-5":{"draws":0,"losses":10,"wins":0},"claude-fable-5-1":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":12,"losses":26,"wins":10},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":9,"losses":45,"wins":6},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":10,"losses":17,"wins":11},"deepseek/deepseek-v4-pro":{"draws":6,"losses":13,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":9,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":11,"wins":7},"google/gemini-3.5-flash-lite":{"draws":33,"losses":73,"wins":24},"google/gemini-3.6-flash":{"draws":37,"losses":48,"wins":21},"google/gemini-3.8-flash":{"draws":4,"losses":12,"wins":0},"google/gemma-4-31b-it":{"draws":6,"losses":5,"wins":1},"gpt-4.1":{"draws":4,"losses":4,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":8,"wins":0},"gpt-5":{"draws":2,"losses":4,"wins":0},"gpt-5.4":{"draws":6,"losses":34,"wins":8},"gpt-5.4-mini":{"draws":1,"losses":3,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":15,"wins":5},"gpt-5.5":{"draws":6,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":10,"losses":26,"wins":16},"gpt-5.6-sol":{"draws":0,"losses":40,"wins":6},"gpt-5.6-terra":{"draws":2,"losses":14,"wins":2},"gpt-6-astra":{"draws":0,"losses":8,"wins":0},"gpt-6-luna":{"draws":3,"losses":3,"wins":0},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":8,"losses":7,"wins":5},"inclusionai/ling-3.0-flash":{"draws":13,"losses":15,"wins":10},"meituan/longcat-2.0":{"draws":11,"losses":19,"wins":22},"meta/muse-glimmer-30b":{"draws":12,"losses":10,"wins":2},"meta/muse-spark-1.2":{"draws":0,"losses":27,"wins":3},"meta/muse-spark-1.3":{"draws":6,"losses":9,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":31,"wins":7},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":4},"o3":{"draws":13,"losses":47,"wins":14},"openai/gpt-oss-120b":{"draws":10,"losses":12,"wins":6},"poolside/laguna-s-2.1":{"draws":20,"losses":17,"wins":1},"qwen/qwen3.7-max":{"draws":4,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":13,"wins":3},"qwen/qwen3.8-27b":{"draws":4,"losses":9,"wins":1},"qwen/qwen3.8-flash":{"draws":7,"losses":4,"wins":3},"qwen/qwen3.8-max":{"draws":8,"losses":12,"wins":2},"qwen/qwen3.8-max-0902":{"draws":3,"losses":1,"wins":0},"stealth/ox-alpha":{"draws":7,"losses":32,"wins":15},"stepfun/step-3.7-flash":{"draws":7,"losses":9,"wins":6},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":0},"tencent/hy4-preview":{"draws":7,"losses":11,"wins":2},"thinkingmachines/inkling":{"draws":24,"losses":12,"wins":14},"thinkingmachines/inkling-small":{"draws":15,"losses":8,"wins":7},"x-ai/grok-4.5":{"draws":9,"losses":28,"wins":3},"x-ai/grok-4.6":{"draws":8,"losses":11,"wins":1},"x-ai/grok-4.7":{"draws":2,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":7,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":12,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":1,"wins":2},"z-ai/glm-5.2":{"draws":14,"losses":13,"wins":3},"z-ai/glm-5.3":{"draws":2,"losses":14,"wins":2},"z-ai/glm-5.3-flash":{"draws":7,"losses":6,"wins":3},"z-ai/glm-5.3-flashx":{"draws":0,"losses":5,"wins":1}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":10,"losses":17,"wins":11},"claude-fable-5":{"draws":6,"losses":14,"wins":2},"claude-fable-5-1":{"draws":0,"losses":20,"wins":0},"claude-opus-4-5":{"draws":12,"losses":20,"wins":2},"claude-opus-4-8":{"draws":0,"losses":2,"wins":0},"claude-opus-5":{"draws":2,"losses":12,"wins":0},"claude-opus-5-5":{"draws":3,"losses":7,"wins":0},"claude-sonnet-5":{"draws":19,"losses":28,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":16,"losses":14,"wins":10},"deepseek/deepseek-v4-pro":{"draws":11,"losses":12,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":8,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":2,"wins":4},"google/gemini-3.5-flash":{"draws":10,"losses":20,"wins":8},"google/gemini-3.5-flash-lite":{"draws":27,"losses":25,"wins":24},"google/gemini-3.6-flash":{"draws":22,"losses":23,"wins":7},"google/gemini-3.8-flash":{"draws":12,"losses":17,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":0},"gpt-4.1":{"draws":0,"losses":2,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":2},"gpt-5":{"draws":2,"losses":4,"wins":2},"gpt-5.4":{"draws":13,"losses":15,"wins":6},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":5,"wins":5},"gpt-5.5":{"draws":5,"losses":5,"wins":0},"gpt-5.6-luna":{"draws":19,"losses":18,"wins":7},"gpt-5.6-sol":{"draws":2,"losses":20,"wins":0},"gpt-5.6-terra":{"draws":10,"losses":29,"wins":3},"gpt-6-astra":{"draws":1,"losses":13,"wins":0},"gpt-6-luna":{"draws":2,"losses":2,"wins":2},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":16,"losses":9,"wins":9},"inclusionai/ling-3.0-flash":{"draws":2,"losses":2,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":4,"wins":2},"meta/muse-glimmer-30b":{"draws":19,"losses":8,"wins":13},"meta/muse-spark-1.2":{"draws":6,"losses":17,"wins":1},"meta/muse-spark-1.3":{"draws":8,"losses":15,"wins":7},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":8,"losses":4,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":4},"moonshotai/kimi-k3":{"draws":13,"losses":16,"wins":3},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":4},"o3":{"draws":8,"losses":24,"wins":10},"openai/gpt-oss-120b":{"draws":11,"losses":7,"wins":6},"poolside/laguna-s-2.1":{"draws":11,"losses":10,"wins":7},"qwen/qwen3.7-max":{"draws":3,"losses":4,"wins":5},"qwen/qwen3.7-plus":{"draws":4,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":9,"wins":1},"qwen/qwen3.8-27b":{"draws":2,"losses":15,"wins":3},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":4},"qwen/qwen3.8-max":{"draws":13,"losses":8,"wins":3},"qwen/qwen3.8-max-0902":{"draws":4,"losses":7,"wins":1},"stealth/ox-alpha":{"draws":31,"losses":53,"wins":10},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":4},"tencent/hy4-preview":{"draws":9,"losses":7,"wins":4},"thinkingmachines/inkling":{"draws":10,"losses":14,"wins":12},"thinkingmachines/inkling-small":{"draws":14,"losses":8,"wins":24},"x-ai/grok-4.5":{"draws":7,"losses":11,"wins":6},"x-ai/grok-4.6":{"draws":10,"losses":11,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":8,"wins":0},"xiaomi/mimo-v2.5":{"draws":13,"losses":5,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":1},"z-ai/glm-5.2":{"draws":24,"losses":13,"wins":11},"z-ai/glm-5.3":{"draws":7,"losses":13,"wins":0},"z-ai/glm-5.3-flash":{"draws":11,"losses":14,"wins":3},"z-ai/glm-5.3-flashx":{"draws":4,"losses":1,"wins":1}},"poolside/laguna-s-2.1":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":8,"wins":6},"claude-fable-5":{"draws":4,"losses":15,"wins":7},"claude-fable-5-1":{"draws":2,"losses":28,"wins":0},"claude-opus-4-5":{"draws":35,"losses":36,"wins":17},"claude-opus-4-8":{"draws":13,"losses":40,"wins":9},"claude-opus-5":{"draws":9,"losses":121,"wins":10},"claude-opus-5-5":{"draws":0,"losses":14,"wins":0},"claude-sonnet-5":{"draws":8,"losses":17,"wins":1},"cohere/north-mini-code":{"draws":29,"losses":18,"wins":3},"deepseek/deepseek-v4-flash":{"draws":25,"losses":16,"wins":23},"deepseek/deepseek-v4-pro":{"draws":6,"losses":13,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":17,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":2,"wins":1},"google/gemini-3.1-flash-lite":{"draws":10,"losses":14,"wins":16},"google/gemini-3.5-flash":{"draws":9,"losses":16,"wins":11},"google/gemini-3.5-flash-lite":{"draws":25,"losses":31,"wins":46},"google/gemini-3.6-flash":{"draws":33,"losses":37,"wins":32},"google/gemini-3.8-flash":{"draws":6,"losses":18,"wins":6},"google/gemma-4-31b-it":{"draws":4,"losses":13,"wins":23},"gpt-4.1":{"draws":6,"losses":13,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":1,"wins":3},"gpt-5":{"draws":18,"losses":15,"wins":23},"gpt-5.4":{"draws":14,"losses":5,"wins":3},"gpt-5.4-mini":{"draws":26,"losses":11,"wins":11},"gpt-5.4-nano":{"draws":31,"losses":22,"wins":37},"gpt-5.5":{"draws":33,"losses":21,"wins":16},"gpt-5.6-luna":{"draws":13,"losses":8,"wins":11},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":2},"gpt-5.6-terra":{"draws":15,"losses":12,"wins":7},"gpt-6-astra":{"draws":5,"losses":19,"wins":0},"gpt-6-luna":{"draws":3,"losses":8,"wins":7},"gpt-6-sol":{"draws":2,"losses":14,"wins":2},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":6,"wins":8},"inclusionai/ling-3.0-flash":{"draws":40,"losses":12,"wins":28},"meituan/longcat-2.0":{"draws":37,"losses":23,"wins":28},"meta/muse-glimmer-30b":{"draws":10,"losses":7,"wins":5},"meta/muse-spark-1.2":{"draws":7,"losses":13,"wins":10},"meta/muse-spark-1.3":{"draws":2,"losses":13,"wins":9},"minimax/minimax-m3":{"draws":14,"losses":15,"wins":17},"mistralai/mistral-medium-3-5":{"draws":5,"losses":5,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":3,"wins":15},"moonshotai/kimi-k3":{"draws":24,"losses":17,"wins":21},"nex-agi/nex-n2-pro":{"draws":17,"losses":6,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":10,"wins":19},"o3":{"draws":9,"losses":23,"wins":14},"openai/gpt-oss-120b":{"draws":2,"losses":3,"wins":13},"poolside/laguna-s-2.1":{"draws":31,"losses":21,"wins":28},"qwen/qwen3.7-max":{"draws":16,"losses":14,"wins":14},"qwen/qwen3.7-plus":{"draws":18,"losses":3,"wins":19},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":13,"wins":2},"qwen/qwen3.8-27b":{"draws":5,"losses":11,"wins":8},"qwen/qwen3.8-flash":{"draws":9,"losses":8,"wins":5},"qwen/qwen3.8-max":{"draws":8,"losses":7,"wins":8},"qwen/qwen3.8-max-0902":{"draws":1,"losses":3,"wins":4},"stealth/ox-alpha":{"draws":27,"losses":47,"wins":21},"stepfun/step-3.7-flash":{"draws":4,"losses":17,"wins":11},"tencent/hy3-preview":{"draws":8,"losses":16,"wins":12},"tencent/hy4-preview":{"draws":12,"losses":14,"wins":6},"thinkingmachines/inkling":{"draws":25,"losses":22,"wins":33},"thinkingmachines/inkling-small":{"draws":13,"losses":7,"wins":10},"x-ai/grok-4.5":{"draws":16,"losses":57,"wins":21},"x-ai/grok-4.6":{"draws":8,"losses":10,"wins":6},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":3},"x-ai/grok-build-0.1":{"draws":7,"losses":10,"wins":5},"xiaomi/mimo-v2.5":{"draws":35,"losses":33,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":21,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":8,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":50,"losses":37,"wins":31},"z-ai/glm-5.3":{"draws":4,"losses":17,"wins":1},"z-ai/glm-5.3-flash":{"draws":6,"losses":20,"wins":4},"z-ai/glm-5.3-flashx":{"draws":0,"losses":3,"wins":3}},"qwen/qwen3.7-max":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":9,"wins":3},"claude-fable-5":{"draws":2,"losses":9,"wins":1},"claude-fable-5-1":{"draws":0,"losses":14,"wins":0},"claude-opus-4-5":{"draws":17,"losses":30,"wins":7},"claude-opus-4-8":{"draws":10,"losses":19,"wins":7},"claude-opus-5":{"draws":12,"losses":59,"wins":1},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":3,"losses":10,"wins":3},"cohere/north-mini-code":{"draws":7,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":17,"losses":10,"wins":17},"deepseek/deepseek-v4-pro":{"draws":4,"losses":6,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":9,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":4,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":8,"wins":23},"google/gemini-3.5-flash":{"draws":4,"losses":5,"wins":7},"google/gemini-3.5-flash-lite":{"draws":9,"losses":14,"wins":3},"google/gemini-3.6-flash":{"draws":10,"losses":24,"wins":4},"google/gemini-3.8-flash":{"draws":4,"losses":7,"wins":5},"google/gemma-4-31b-it":{"draws":2,"losses":10,"wins":18},"gpt-4.1":{"draws":3,"losses":0,"wins":7},"gpt-5":{"draws":11,"losses":10,"wins":3},"gpt-5.4":{"draws":2,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":15,"losses":7,"wins":14},"gpt-5.4-nano":{"draws":14,"losses":15,"wins":17},"gpt-5.5":{"draws":15,"losses":6,"wins":7},"gpt-5.6-luna":{"draws":0,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":1,"losses":4,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":10,"wins":4},"gpt-6-astra":{"draws":2,"losses":8,"wins":0},"gpt-6-luna":{"draws":0,"losses":4,"wins":0},"gpt-6-sol":{"draws":0,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":5,"wins":3},"inclusionai/ling-3.0-flash":{"draws":17,"losses":4,"wins":15},"meituan/longcat-2.0":{"draws":11,"losses":3,"wins":8},"meta/muse-glimmer-30b":{"draws":3,"losses":2,"wins":5},"meta/muse-spark-1.2":{"draws":1,"losses":5,"wins":0},"meta/muse-spark-1.3":{"draws":1,"losses":6,"wins":3},"minimax/minimax-m3":{"draws":15,"losses":4,"wins":19},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":7,"losses":16,"wins":5},"nex-agi/nex-n2-pro":{"draws":11,"losses":3,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":6,"wins":14},"o3":{"draws":7,"losses":18,"wins":5},"openai/gpt-oss-120b":{"draws":5,"losses":1,"wins":4},"poolside/laguna-s-2.1":{"draws":12,"losses":17,"wins":9},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":4},"qwen/qwen3.7-plus":{"draws":16,"losses":6,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":6,"wins":1},"qwen/qwen3.8-27b":{"draws":0,"losses":9,"wins":5},"qwen/qwen3.8-flash":{"draws":5,"losses":1,"wins":6},"qwen/qwen3.8-max":{"draws":7,"losses":4,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":1},"stealth/ox-alpha":{"draws":7,"losses":24,"wins":13},"stepfun/step-3.7-flash":{"draws":10,"losses":5,"wins":9},"tencent/hy3-preview":{"draws":21,"losses":6,"wins":15},"tencent/hy4-preview":{"draws":5,"losses":3,"wins":0},"thinkingmachines/inkling":{"draws":13,"losses":5,"wins":18},"thinkingmachines/inkling-small":{"draws":4,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":6,"losses":11,"wins":7},"x-ai/grok-4.6":{"draws":3,"losses":4,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":10,"wins":2},"xiaomi/mimo-v2.5":{"draws":35,"losses":15,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":5,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":1},"z-ai/glm-5.2":{"draws":23,"losses":18,"wins":9},"z-ai/glm-5.3":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.3-flashx":{"draws":2,"losses":6,"wins":2}},"qwen/qwen3.7-plus":{"bytedance-seed/seed-2.0-code":{"draws":5,"losses":5,"wins":2},"claude-fable-5":{"draws":0,"losses":6,"wins":0},"claude-fable-5-1":{"draws":3,"losses":1,"wins":0},"claude-opus-4-5":{"draws":36,"losses":18,"wins":6},"claude-opus-4-8":{"draws":8,"losses":18,"wins":6},"claude-opus-5":{"draws":3,"losses":19,"wins":10},"claude-sonnet-5":{"draws":4,"losses":10,"wins":2},"cohere/north-mini-code":{"draws":6,"losses":7,"wins":7},"deepseek/deepseek-v4-flash":{"draws":11,"losses":19,"wins":18},"deepseek/deepseek-v4-pro":{"draws":6,"losses":11,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":1,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":8,"wins":0},"google/gemini-3.1-flash-lite":{"draws":9,"losses":16,"wins":17},"google/gemini-3.5-flash":{"draws":7,"losses":5,"wins":0},"google/gemini-3.5-flash-lite":{"draws":13,"losses":15,"wins":4},"google/gemini-3.6-flash":{"draws":17,"losses":17,"wins":4},"google/gemini-3.8-flash":{"draws":4,"losses":8,"wins":0},"google/gemma-4-31b-it":{"draws":2,"losses":21,"wins":5},"gpt-4.1":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":2,"losses":6,"wins":0},"gpt-5.4":{"draws":1,"losses":17,"wins":0},"gpt-5.4-mini":{"draws":8,"losses":13,"wins":9},"gpt-5.4-nano":{"draws":10,"losses":24,"wins":14},"gpt-5.5":{"draws":17,"losses":19,"wins":2},"gpt-5.6-luna":{"draws":5,"losses":9,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":11,"wins":1},"gpt-5.6-terra":{"draws":2,"losses":4,"wins":0},"gpt-6-astra":{"draws":1,"losses":3,"wins":0},"gpt-6-luna":{"draws":3,"losses":5,"wins":2},"gpt-6-sol":{"draws":0,"losses":2,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":5,"wins":3},"inclusionai/ling-3.0-flash":{"draws":14,"losses":12,"wins":8},"meituan/longcat-2.0":{"draws":6,"losses":12,"wins":0},"meta/muse-glimmer-30b":{"draws":4,"losses":3,"wins":3},"meta/muse-spark-1.2":{"draws":2,"losses":4,"wins":0},"meta/muse-spark-1.3":{"draws":0,"losses":5,"wins":1},"minimax/minimax-m3":{"draws":7,"losses":12,"wins":5},"mistralai/mistral-medium-3-5":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":8,"losses":14,"wins":2},"nex-agi/nex-n2-pro":{"draws":10,"losses":10,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":8,"wins":8},"o3":{"draws":4,"losses":11,"wins":3},"openai/gpt-oss-120b":{"draws":4,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":10,"losses":12,"wins":2},"qwen/qwen3.7-max":{"draws":12,"losses":10,"wins":4},"qwen/qwen3.7-plus":{"draws":2,"losses":6,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":6,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":7,"wins":1},"qwen/qwen3.8-flash":{"draws":7,"losses":7,"wins":2},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":1},"qwen/qwen3.8-max-0902":{"draws":2,"losses":3,"wins":1},"stealth/ox-alpha":{"draws":2,"losses":14,"wins":2},"stepfun/step-3.7-flash":{"draws":6,"losses":6,"wins":8},"tencent/hy3-preview":{"draws":10,"losses":16,"wins":4},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":10,"losses":16,"wins":12},"thinkingmachines/inkling-small":{"draws":2,"losses":4,"wins":2},"x-ai/grok-4.5":{"draws":11,"losses":9,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":4,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":5,"wins":3},"xiaomi/mimo-v2.5":{"draws":28,"losses":31,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":16,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":25,"losses":20,"wins":7},"z-ai/glm-5.3":{"draws":1,"losses":12,"wins":0},"z-ai/glm-5.3-flash":{"draws":4,"losses":5,"wins":1},"z-ai/glm-5.3-flashx":{"draws":0,"losses":3,"wins":1}},"qwen/qwen3.8-2.4t-a95b":{"bytedance-seed/seed-2.0-code":{"draws":16,"losses":12,"wins":14},"claude-fable-5":{"draws":11,"losses":23,"wins":10},"claude-fable-5-1":{"draws":2,"losses":48,"wins":0},"claude-opus-4-5":{"draws":12,"losses":17,"wins":17},"claude-opus-4-8":{"draws":10,"losses":10,"wins":4},"claude-opus-5":{"draws":1,"losses":14,"wins":5},"claude-opus-5-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":18,"losses":9,"wins":19},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":20,"losses":8,"wins":30},"deepseek/deepseek-v4-pro":{"draws":15,"losses":11,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":13,"losses":17,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":9,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":11,"losses":17,"wins":16},"google/gemini-3.5-flash-lite":{"draws":29,"losses":17,"wins":28},"google/gemini-3.6-flash":{"draws":20,"losses":43,"wins":23},"google/gemini-3.8-flash":{"draws":7,"losses":24,"wins":17},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":0,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":2,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":2,"wins":7},"gpt-5.4":{"draws":11,"losses":10,"wins":21},"gpt-5.4-mini":{"draws":7,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":6,"losses":4,"wins":6},"gpt-5.5":{"draws":0,"losses":6,"wins":0},"gpt-5.6-luna":{"draws":19,"losses":12,"wins":15},"gpt-5.6-sol":{"draws":11,"losses":29,"wins":8},"gpt-5.6-terra":{"draws":12,"losses":9,"wins":25},"gpt-6-astra":{"draws":5,"losses":36,"wins":1},"gpt-6-luna":{"draws":2,"losses":3,"wins":3},"gpt-6-sol":{"draws":0,"losses":5,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":14,"losses":4,"wins":16},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":12},"meituan/longcat-2.0":{"draws":8,"losses":5,"wins":15},"meta/muse-glimmer-30b":{"draws":17,"losses":11,"wins":10},"meta/muse-spark-1.2":{"draws":5,"losses":11,"wins":20},"meta/muse-spark-1.3":{"draws":12,"losses":13,"wins":17},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":9},"mistralai/mistral-medium-3-5":{"draws":6,"losses":2,"wins":24},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":14,"losses":16,"wins":22},"nex-agi/nex-n2-pro":{"draws":0,"losses":3,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":2},"o3":{"draws":7,"losses":12,"wins":23},"openai/gpt-oss-120b":{"draws":13,"losses":6,"wins":13},"poolside/laguna-s-2.1":{"draws":12,"losses":5,"wins":19},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":5},"qwen/qwen3.7-plus":{"draws":1,"losses":3,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"losses":12,"wins":9},"qwen/qwen3.8-27b":{"draws":5,"losses":12,"wins":15},"qwen/qwen3.8-flash":{"draws":7,"losses":14,"wins":13},"qwen/qwen3.8-max":{"draws":15,"losses":22,"wins":13},"qwen/qwen3.8-max-0902":{"draws":5,"losses":9,"wins":2},"stealth/ox-alpha":{"draws":38,"losses":62,"wins":53},"stepfun/step-3.7-flash":{"draws":4,"losses":4,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":12,"losses":19,"wins":11},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":15},"thinkingmachines/inkling-small":{"draws":18,"losses":7,"wins":37},"x-ai/grok-4.5":{"draws":8,"losses":19,"wins":11},"x-ai/grok-4.6":{"draws":16,"losses":19,"wins":13},"x-ai/grok-4.7":{"draws":2,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":8,"losses":3,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":2,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":17,"losses":21,"wins":26},"z-ai/glm-5.3":{"draws":10,"losses":18,"wins":4},"z-ai/glm-5.3-flash":{"draws":15,"losses":14,"wins":15},"z-ai/glm-5.3-flashx":{"draws":5,"losses":7,"wins":2}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":1,"wins":2},"claude-fable-5":{"draws":5,"losses":6,"wins":1},"claude-fable-5-1":{"draws":2,"losses":10,"wins":0},"claude-opus-4-5":{"draws":7,"losses":2,"wins":1},"claude-opus-4-8":{"draws":3,"losses":2,"wins":1},"claude-opus-5":{"draws":0,"losses":8,"wins":0},"claude-opus-5-5":{"draws":0,"losses":2,"wins":0},"claude-sonnet-5":{"draws":6,"losses":4,"wins":0},"cohere/north-mini-code":{"draws":5,"losses":0,"wins":1},"deepseek/deepseek-v4-flash":{"draws":10,"losses":0,"wins":2},"deepseek/deepseek-v4-pro":{"draws":11,"losses":0,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":2,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":0,"wins":0},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":9,"losses":4,"wins":5},"google/gemini-3.5-flash-lite":{"draws":20,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":15,"losses":7,"wins":2},"google/gemini-3.8-flash":{"draws":9,"losses":7,"wins":0},"google/gemma-4-31b-it":{"draws":4,"losses":0,"wins":0},"gpt-5":{"draws":3,"losses":2,"wins":3},"gpt-5.4":{"draws":13,"losses":0,"wins":1},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.5":{"draws":2,"losses":0,"wins":0},"gpt-5.6-luna":{"draws":6,"losses":2,"wins":2},"gpt-5.6-sol":{"draws":6,"losses":4,"wins":2},"gpt-5.6-terra":{"draws":7,"losses":3,"wins":2},"gpt-6-astra":{"draws":0,"losses":8,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":8,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":3},"meta/muse-glimmer-30b":{"draws":10,"losses":0,"wins":0},"meta/muse-spark-1.2":{"draws":3,"losses":4,"wins":1},"meta/muse-spark-1.3":{"draws":2,"losses":6,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":7,"losses":0,"wins":3},"moonshotai/kimi-k3":{"draws":8,"losses":0,"wins":0},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"o3":{"draws":13,"losses":1,"wins":0},"openai/gpt-oss-120b":{"draws":12,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":0,"losses":4,"wins":2},"qwen/qwen3.8-flash":{"draws":7,"losses":1,"wins":0},"qwen/qwen3.8-max":{"draws":7,"losses":8,"wins":1},"stealth/ox-alpha":{"draws":22,"losses":9,"wins":7},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":0},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":0},"tencent/hy4-preview":{"draws":10,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":11,"losses":2,"wins":1},"thinkingmachines/inkling-small":{"draws":10,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":4,"losses":2,"wins":4},"x-ai/grok-4.6":{"draws":5,"losses":3,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":1},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":15,"losses":4,"wins":3},"z-ai/glm-5.3":{"draws":3,"losses":4,"wins":1},"z-ai/glm-5.3-flash":{"draws":12,"losses":8,"wins":2},"z-ai/glm-5.3-flashx":{"draws":2,"losses":1,"wins":1}},"qwen/qwen3.8-flash":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":15,"wins":16},"claude-fable-5":{"draws":11,"losses":25,"wins":0},"claude-fable-5-1":{"draws":4,"losses":32,"wins":0},"claude-opus-4-5":{"draws":15,"losses":21,"wins":6},"claude-opus-4-8":{"draws":2,"losses":8,"wins":2},"claude-opus-5":{"draws":6,"losses":17,"wins":1},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":21,"losses":25,"wins":8},"cohere/north-mini-code":{"draws":8,"losses":2,"wins":2},"deepseek/deepseek-v4-flash":{"draws":19,"losses":17,"wins":20},"deepseek/deepseek-v4-pro":{"draws":16,"losses":22,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":20,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":2},"google/gemini-3.1-flash-lite":{"draws":8,"losses":2,"wins":2},"google/gemini-3.5-flash":{"draws":15,"losses":29,"wins":4},"google/gemini-3.5-flash-lite":{"draws":32,"losses":24,"wins":36},"google/gemini-3.6-flash":{"draws":38,"losses":35,"wins":7},"google/gemini-3.8-flash":{"draws":12,"losses":35,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":5,"wins":5},"gpt-4.1":{"draws":0,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":2,"losses":7,"wins":3},"gpt-5.4":{"draws":11,"losses":11,"wins":12},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":4},"gpt-5.4-nano":{"draws":4,"losses":5,"wins":3},"gpt-5.5":{"draws":7,"losses":7,"wins":0},"gpt-5.6-luna":{"draws":17,"losses":19,"wins":10},"gpt-5.6-sol":{"draws":4,"losses":26,"wins":6},"gpt-5.6-terra":{"draws":8,"losses":21,"wins":9},"gpt-6-astra":{"draws":3,"losses":27,"wins":0},"gpt-6-luna":{"draws":0,"losses":2,"wins":2},"gpt-6-sol":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":1,"wins":2},"inception/mercury-2.5-preview":{"draws":20,"losses":7,"wins":17},"inclusionai/ling-3.0-flash":{"draws":10,"losses":7,"wins":13},"meituan/longcat-2.0":{"draws":17,"losses":6,"wins":13},"meta/muse-glimmer-30b":{"draws":29,"losses":11,"wins":8},"meta/muse-spark-1.2":{"draws":11,"losses":14,"wins":5},"meta/muse-spark-1.3":{"draws":12,"losses":28,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":2},"mistralai/mistral-medium-3-5":{"draws":16,"losses":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":21,"wins":3},"nex-agi/nex-n2-pro":{"draws":16,"losses":1,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":11,"losses":8,"wins":7},"o3":{"draws":16,"losses":28,"wins":10},"openai/gpt-oss-120b":{"draws":20,"losses":18,"wins":14},"poolside/laguna-s-2.1":{"draws":15,"losses":12,"wins":13},"qwen/qwen3.7-max":{"draws":11,"losses":8,"wins":1},"qwen/qwen3.7-plus":{"draws":7,"losses":5,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":18,"losses":21,"wins":5},"qwen/qwen3.8-27b":{"draws":5,"losses":15,"wins":2},"qwen/qwen3.8-flash":{"draws":7,"losses":5,"wins":0},"qwen/qwen3.8-max":{"draws":18,"losses":12,"wins":8},"qwen/qwen3.8-max-0902":{"draws":3,"losses":3,"wins":2},"stealth/ox-alpha":{"draws":41,"losses":71,"wins":30},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":5},"tencent/hy3-preview":{"draws":9,"losses":5,"wins":0},"tencent/hy4-preview":{"draws":9,"losses":24,"wins":5},"thinkingmachines/inkling":{"draws":17,"losses":11,"wins":14},"thinkingmachines/inkling-small":{"draws":26,"losses":18,"wins":18},"x-ai/grok-4.5":{"draws":9,"losses":12,"wins":5},"x-ai/grok-4.6":{"draws":19,"losses":18,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":7,"losses":3,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":7,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":30,"losses":18,"wins":16},"z-ai/glm-5.3":{"draws":11,"losses":27,"wins":4},"z-ai/glm-5.3-flash":{"draws":16,"losses":15,"wins":3},"z-ai/glm-5.3-flashx":{"draws":3,"losses":5,"wins":0}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":21,"wins":13},"claude-fable-5":{"draws":8,"losses":7,"wins":17},"claude-fable-5-1":{"draws":0,"losses":35,"wins":3},"claude-opus-4-5":{"draws":15,"losses":16,"wins":13},"claude-opus-4-8":{"draws":1,"losses":5,"wins":4},"claude-opus-5":{"draws":5,"losses":17,"wins":2},"claude-opus-5-5":{"draws":1,"losses":11,"wins":0},"claude-sonnet-5":{"draws":20,"losses":21,"wins":12},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":29,"losses":7,"wins":18},"deepseek/deepseek-v4-pro":{"draws":17,"losses":11,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":14,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":4,"wins":1},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":1},"google/gemini-3.5-flash":{"draws":15,"losses":10,"wins":11},"google/gemini-3.5-flash-lite":{"draws":35,"losses":25,"wins":15},"google/gemini-3.6-flash":{"draws":27,"losses":26,"wins":27},"google/gemini-3.8-flash":{"draws":10,"losses":12,"wins":20},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":0,"losses":2,"wins":10},"gpt-5.4":{"draws":20,"losses":11,"wins":23},"gpt-5.4-mini":{"draws":3,"losses":4,"wins":1},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":6},"gpt-5.5":{"draws":4,"losses":8,"wins":8},"gpt-5.6-luna":{"draws":26,"losses":9,"wins":24},"gpt-5.6-sol":{"draws":9,"losses":18,"wins":10},"gpt-5.6-terra":{"draws":21,"losses":10,"wins":15},"gpt-6-astra":{"draws":1,"losses":27,"wins":2},"gpt-6-luna":{"draws":1,"losses":2,"wins":3},"gpt-6-sol":{"draws":0,"losses":4,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":23,"losses":6,"wins":13},"inclusionai/ling-3.0-flash":{"draws":9,"losses":5,"wins":11},"meituan/longcat-2.0":{"draws":23,"losses":9,"wins":9},"meta/muse-glimmer-30b":{"draws":18,"losses":13,"wins":19},"meta/muse-spark-1.2":{"draws":10,"losses":13,"wins":11},"meta/muse-spark-1.3":{"draws":6,"losses":10,"wins":8},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":2},"mistralai/mistral-medium-3-5":{"draws":11,"losses":7,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":12,"losses":13,"wins":9},"nex-agi/nex-n2-pro":{"draws":4,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":4,"wins":2},"o3":{"draws":10,"losses":15,"wins":17},"openai/gpt-oss-120b":{"draws":27,"losses":5,"wins":18},"poolside/laguna-s-2.1":{"draws":12,"losses":12,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":15,"wins":9},"qwen/qwen3.8-27b":{"draws":5,"losses":9,"wins":8},"qwen/qwen3.8-flash":{"draws":10,"losses":8,"wins":6},"qwen/qwen3.8-max":{"draws":19,"losses":27,"wins":12},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":47,"losses":53,"wins":44},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":7},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":4},"tencent/hy4-preview":{"draws":9,"losses":19,"wins":14},"thinkingmachines/inkling":{"draws":15,"losses":8,"wins":13},"thinkingmachines/inkling-small":{"draws":38,"losses":22,"wins":32},"x-ai/grok-4.5":{"draws":18,"losses":12,"wins":12},"x-ai/grok-4.6":{"draws":10,"losses":17,"wins":9},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":11,"losses":3,"wins":12},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":4,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":1,"wins":0},"z-ai/glm-5.2":{"draws":25,"losses":15,"wins":22},"z-ai/glm-5.3":{"draws":10,"losses":15,"wins":9},"z-ai/glm-5.3-flash":{"draws":11,"losses":14,"wins":15},"z-ai/glm-5.3-flashx":{"draws":1,"losses":1,"wins":2}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":2,"wins":0},"claude-fable-5":{"draws":2,"losses":5,"wins":1},"claude-fable-5-1":{"draws":0,"losses":8,"wins":0},"claude-opus-4-5":{"draws":2,"losses":5,"wins":5},"claude-opus-4-8":{"draws":2,"losses":1,"wins":5},"claude-opus-5":{"draws":1,"losses":7,"wins":0},"claude-opus-5-5":{"draws":1,"losses":13,"wins":0},"claude-sonnet-5":{"draws":4,"losses":2,"wins":2},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":4,"losses":0,"wins":12},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":5,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":8,"wins":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":2,"losses":2,"wins":2},"google/gemini-3.5-flash-lite":{"draws":6,"losses":3,"wins":11},"google/gemini-3.6-flash":{"draws":5,"losses":6,"wins":3},"google/gemini-3.8-flash":{"draws":1,"losses":1,"wins":0},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":0,"wins":6},"gpt-5":{"draws":4,"losses":0,"wins":2},"gpt-5.4":{"draws":3,"losses":11,"wins":2},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":4,"losses":3,"wins":1},"gpt-5.5":{"draws":6,"losses":1,"wins":1},"gpt-5.6-luna":{"draws":7,"losses":0,"wins":5},"gpt-5.6-sol":{"draws":5,"losses":7,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":0,"wins":3},"gpt-6-astra":{"draws":0,"losses":14,"wins":2},"gpt-6-luna":{"draws":12,"losses":3,"wins":1},"gpt-6-sol":{"draws":3,"losses":12,"wins":3},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":5,"losses":1,"wins":8},"meta/muse-glimmer-30b":{"draws":7,"losses":0,"wins":3},"meta/muse-spark-1.2":{"draws":2,"losses":2,"wins":4},"meta/muse-spark-1.3":{"draws":4,"losses":4,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":3},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":0,"wins":4},"o3":{"draws":0,"losses":4,"wins":8},"openai/gpt-oss-120b":{"draws":8,"losses":1,"wins":7},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":0,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":1},"qwen/qwen3.8-max":{"draws":1,"losses":2,"wins":3},"qwen/qwen3.8-max-0902":{"draws":5,"losses":13,"wins":6},"stealth/ox-alpha":{"draws":9,"losses":13,"wins":10},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":5},"tencent/hy3-preview":{"draws":1,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":0,"losses":4,"wins":4},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":4},"thinkingmachines/inkling-small":{"draws":2,"losses":2,"wins":0},"x-ai/grok-4.5":{"draws":2,"losses":4,"wins":0},"x-ai/grok-4.6":{"draws":4,"losses":8,"wins":0},"x-ai/grok-4.7":{"draws":2,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":10,"losses":3,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"wins":3},"xiaomi/mimo-v2.6-flash":{"draws":8,"losses":14,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":7,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":3,"wins":6},"z-ai/glm-5.3":{"draws":6,"losses":6,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.3-flashx":{"draws":6,"losses":15,"wins":9}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":61,"losses":33,"wins":62},"claude-fable-5":{"draws":41,"losses":94,"wins":23},"claude-fable-5-1":{"draws":10,"losses":153,"wins":1},"claude-opus-4-5":{"draws":63,"losses":48,"wins":39},"claude-opus-4-8":{"draws":17,"losses":12,"wins":11},"claude-opus-5":{"draws":9,"losses":70,"wins":5},"claude-opus-5-5":{"draws":4,"losses":32,"wins":0},"claude-sonnet-5":{"draws":60,"losses":52,"wins":48},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":16},"deepseek/deepseek-v4-flash":{"draws":95,"losses":48,"wins":41},"deepseek/deepseek-v4-pro":{"draws":77,"losses":59,"wins":44},"deepseek/deepseek-v4-pro-0813":{"draws":70,"losses":57,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":22,"wins":14},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":58,"losses":79,"wins":43},"google/gemini-3.5-flash-lite":{"draws":122,"losses":88,"wins":112},"google/gemini-3.6-flash":{"draws":89,"losses":111,"wins":86},"google/gemini-3.8-flash":{"draws":57,"losses":78,"wins":27},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":15},"gpt-4.1":{"draws":9,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":20,"losses":9,"wins":13},"gpt-5.4":{"draws":74,"losses":69,"wins":17},"gpt-5.4-mini":{"draws":10,"losses":14,"wins":14},"gpt-5.4-nano":{"draws":11,"losses":7,"wins":24},"gpt-5.5":{"draws":16,"losses":7,"wins":5},"gpt-5.6-luna":{"draws":82,"losses":46,"wins":42},"gpt-5.6-sol":{"draws":29,"losses":89,"wins":26},"gpt-5.6-terra":{"draws":76,"losses":46,"wins":38},"gpt-6-astra":{"draws":13,"losses":121,"wins":0},"gpt-6-luna":{"draws":12,"losses":6,"wins":4},"gpt-6-sol":{"draws":7,"losses":17,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":19,"losses":1,"wins":6},"inception/mercury-2.5-preview":{"draws":55,"losses":10,"wins":51},"inclusionai/ling-3.0-flash":{"draws":25,"losses":12,"wins":15},"meituan/longcat-2.0":{"draws":37,"losses":13,"wins":63},"meta/muse-glimmer-30b":{"draws":80,"losses":30,"wins":60},"meta/muse-spark-1.2":{"draws":42,"losses":43,"wins":49},"meta/muse-spark-1.3":{"draws":48,"losses":57,"wins":33},"minimax/minimax-m3":{"draws":15,"losses":3,"wins":14},"mistralai/mistral-medium-3-5":{"draws":44,"losses":17,"wins":47},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":3,"wins":2},"moonshotai/kimi-k3":{"draws":58,"losses":42,"wins":38},"nex-agi/nex-n2-pro":{"draws":7,"losses":5,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":7,"wins":17},"o3":{"draws":37,"losses":74,"wins":51},"openai/gpt-oss-120b":{"draws":77,"losses":28,"wins":51},"poolside/laguna-s-2.1":{"draws":59,"losses":23,"wins":42},"qwen/qwen3.7-max":{"draws":11,"losses":10,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":52,"losses":52,"wins":42},"qwen/qwen3.8-27b":{"draws":36,"losses":33,"wins":29},"qwen/qwen3.8-flash":{"draws":48,"losses":30,"wins":20},"qwen/qwen3.8-max":{"draws":61,"losses":73,"wins":42},"qwen/qwen3.8-max-0902":{"draws":8,"losses":19,"wins":9},"stealth/ox-alpha":{"draws":171,"losses":288,"wins":174},"stepfun/step-3.7-flash":{"draws":12,"losses":12,"wins":18},"tencent/hy3-preview":{"draws":16,"losses":2,"wins":8},"tencent/hy4-preview":{"draws":62,"losses":81,"wins":31},"thinkingmachines/inkling":{"draws":58,"losses":19,"wins":53},"thinkingmachines/inkling-small":{"draws":94,"losses":32,"wins":68},"x-ai/grok-4.5":{"draws":47,"losses":43,"wins":32},"x-ai/grok-4.6":{"draws":71,"losses":62,"wins":33},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":3},"x-ai/grok-build-0.1":{"draws":9,"losses":5,"wins":10},"xiaomi/mimo-v2.5":{"draws":28,"losses":19,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":11,"wins":11},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":11,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":6,"wins":4},"z-ai/glm-5.2":{"draws":99,"losses":59,"wins":72},"z-ai/glm-5.3":{"draws":31,"losses":83,"wins":22},"z-ai/glm-5.3-flash":{"draws":61,"losses":73,"wins":38},"z-ai/glm-5.3-flashx":{"draws":4,"losses":23,"wins":9}},"stepfun/step-3.7-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":8,"wins":12},"claude-fable-5":{"draws":0,"losses":18,"wins":2},"claude-fable-5-1":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":8,"losses":37,"wins":13},"claude-opus-4-8":{"draws":0,"losses":15,"wins":1},"claude-opus-5":{"draws":0,"losses":16,"wins":0},"claude-opus-5-5":{"draws":0,"losses":14,"wins":0},"claude-sonnet-5":{"draws":6,"losses":20,"wins":18},"cohere/north-mini-code":{"draws":4,"losses":3,"wins":5},"deepseek/deepseek-v4-flash":{"draws":5,"losses":13,"wins":12},"deepseek/deepseek-v4-pro":{"draws":6,"losses":17,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":11,"wins":5},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":2,"losses":1,"wins":9},"google/gemini-3.5-flash":{"draws":6,"losses":17,"wins":7},"google/gemini-3.5-flash-lite":{"draws":26,"losses":45,"wins":51},"google/gemini-3.6-flash":{"draws":12,"losses":70,"wins":16},"google/gemini-3.8-flash":{"draws":4,"losses":15,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":1,"losses":1,"wins":2},"gpt-5.4":{"draws":6,"losses":30,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":3},"gpt-5.4-nano":{"draws":6,"losses":12,"wins":4},"gpt-5.5":{"draws":2,"losses":6,"wins":2},"gpt-5.6-luna":{"draws":12,"losses":16,"wins":18},"gpt-5.6-sol":{"draws":2,"losses":29,"wins":9},"gpt-5.6-terra":{"draws":5,"losses":13,"wins":6},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"gpt-6-luna":{"draws":0,"losses":3,"wins":3},"gpt-6-sol":{"draws":1,"losses":3,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":3,"losses":5,"wins":12},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":14},"meituan/longcat-2.0":{"draws":6,"losses":25,"wins":27},"meta/muse-glimmer-30b":{"draws":6,"losses":11,"wins":5},"meta/muse-spark-1.2":{"draws":0,"losses":20,"wins":8},"meta/muse-spark-1.3":{"draws":3,"losses":14,"wins":3},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":6,"losses":6,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":12,"losses":29,"wins":9},"nex-agi/nex-n2-pro":{"draws":6,"losses":6,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":4,"wins":2},"o3":{"draws":18,"losses":61,"wins":29},"openai/gpt-oss-120b":{"draws":5,"losses":10,"wins":9},"poolside/laguna-s-2.1":{"draws":12,"losses":8,"wins":22},"qwen/qwen3.7-max":{"draws":4,"losses":8,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":4,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":8,"wins":7},"qwen/qwen3.8-27b":{"draws":2,"losses":13,"wins":3},"qwen/qwen3.8-flash":{"draws":7,"losses":5,"wins":4},"qwen/qwen3.8-max":{"draws":1,"losses":14,"wins":3},"qwen/qwen3.8-max-0902":{"draws":0,"losses":8,"wins":0},"stealth/ox-alpha":{"draws":8,"losses":25,"wins":23},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":2},"tencent/hy4-preview":{"draws":6,"losses":7,"wins":7},"thinkingmachines/inkling":{"draws":14,"losses":19,"wins":23},"thinkingmachines/inkling-small":{"draws":8,"losses":13,"wins":11},"x-ai/grok-4.5":{"draws":4,"losses":25,"wins":11},"x-ai/grok-4.6":{"draws":1,"losses":13,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.5":{"draws":6,"losses":6,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":5,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":10,"losses":12,"wins":10},"z-ai/glm-5.3":{"draws":3,"losses":7,"wins":2},"z-ai/glm-5.3-flash":{"draws":8,"losses":12,"wins":6},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"wins":0}},"tencent/hy3-preview":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":6,"wins":4},"claude-fable-5":{"draws":0,"losses":8,"wins":2},"claude-fable-5-1":{"draws":2,"losses":12,"wins":2},"claude-opus-4-5":{"draws":14,"losses":13,"wins":5},"claude-opus-4-8":{"draws":18,"losses":14,"wins":6},"claude-opus-5":{"draws":16,"losses":31,"wins":7},"claude-opus-5-5":{"draws":0,"losses":14,"wins":0},"claude-sonnet-5":{"draws":9,"losses":8,"wins":3},"cohere/north-mini-code":{"draws":4,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":14,"losses":9,"wins":15},"deepseek/deepseek-v4-pro":{"draws":8,"losses":2,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":5,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":3,"wins":0},"google/gemini-3.1-flash-lite":{"draws":8,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":6,"losses":3,"wins":5},"google/gemini-3.5-flash-lite":{"draws":26,"losses":3,"wins":15},"google/gemini-3.6-flash":{"draws":15,"losses":14,"wins":9},"google/gemini-3.8-flash":{"draws":10,"losses":8,"wins":2},"google/gemma-4-31b-it":{"draws":12,"losses":0,"wins":8},"gpt-4.1":{"draws":8,"losses":4,"wins":6},"gpt-5":{"draws":15,"losses":8,"wins":3},"gpt-5.4":{"draws":10,"losses":2,"wins":0},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":7},"gpt-5.4-nano":{"draws":12,"losses":6,"wins":16},"gpt-5.5":{"draws":15,"losses":13,"wins":6},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":2},"gpt-5.6-sol":{"draws":3,"losses":11,"wins":0},"gpt-5.6-terra":{"draws":3,"losses":5,"wins":0},"gpt-6-astra":{"draws":1,"losses":3,"wins":0},"gpt-6-luna":{"draws":3,"losses":6,"wins":1},"gpt-6-sol":{"draws":3,"losses":9,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":1},"inception/mercury-2.5-preview":{"draws":7,"losses":4,"wins":1},"inclusionai/ling-3.0-flash":{"draws":11,"losses":1,"wins":12},"meituan/longcat-2.0":{"draws":21,"losses":10,"wins":9},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":2},"meta/muse-spark-1.2":{"draws":5,"losses":5,"wins":4},"meta/muse-spark-1.3":{"draws":0,"losses":11,"wins":1},"minimax/minimax-m3":{"draws":18,"losses":8,"wins":16},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":11,"losses":8,"wins":1},"nex-agi/nex-n2-pro":{"draws":16,"losses":5,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":4,"wins":6},"o3":{"draws":11,"losses":12,"wins":1},"openai/gpt-oss-120b":{"draws":8,"losses":3,"wins":3},"poolside/laguna-s-2.1":{"draws":9,"losses":8,"wins":7},"qwen/qwen3.7-max":{"draws":17,"losses":8,"wins":7},"qwen/qwen3.7-plus":{"draws":16,"losses":4,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":5,"wins":3},"qwen/qwen3.8-27b":{"draws":5,"losses":11,"wins":2},"qwen/qwen3.8-flash":{"draws":9,"losses":3,"wins":2},"qwen/qwen3.8-max":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.8-max-0902":{"draws":1,"losses":3,"wins":0},"stealth/ox-alpha":{"draws":18,"losses":8,"wins":8},"stepfun/step-3.7-flash":{"draws":8,"losses":6,"wins":2},"tencent/hy3-preview":{"draws":3,"losses":3,"wins":0},"tencent/hy4-preview":{"draws":5,"losses":2,"wins":3},"thinkingmachines/inkling":{"draws":11,"losses":14,"wins":11},"thinkingmachines/inkling-small":{"draws":7,"losses":1,"wins":0},"x-ai/grok-4.5":{"draws":9,"losses":11,"wins":6},"x-ai/grok-4.6":{"draws":7,"losses":6,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":5,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":33,"losses":14,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":4,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":30,"losses":19,"wins":9},"z-ai/glm-5.3":{"draws":0,"losses":9,"wins":1},"z-ai/glm-5.3-flash":{"draws":6,"losses":4,"wins":2},"z-ai/glm-5.3-flashx":{"draws":2,"losses":2,"wins":0}},"tencent/hy4-preview":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":9,"wins":28},"claude-fable-5":{"draws":9,"losses":25,"wins":0},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-opus-4-5":{"draws":16,"losses":22,"wins":8},"claude-opus-4-8":{"draws":7,"losses":5,"wins":10},"claude-opus-5":{"draws":5,"losses":14,"wins":3},"claude-opus-5-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":22,"losses":17,"wins":13},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":17,"losses":14,"wins":13},"deepseek/deepseek-v4-pro":{"draws":18,"losses":17,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":21,"losses":13,"wins":8},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":4,"wins":4},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":17,"losses":27,"wins":18},"google/gemini-3.5-flash-lite":{"draws":36,"losses":22,"wins":32},"google/gemini-3.6-flash":{"draws":25,"losses":34,"wins":25},"google/gemini-3.8-flash":{"draws":13,"losses":18,"wins":13},"google/gemma-4-31b-it":{"draws":4,"losses":1,"wins":7},"gpt-4.1":{"draws":0,"losses":3,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":4,"losses":5,"wins":7},"gpt-5.4":{"draws":15,"losses":17,"wins":8},"gpt-5.4-mini":{"draws":8,"losses":5,"wins":9},"gpt-5.4-nano":{"draws":5,"losses":2,"wins":5},"gpt-5.5":{"draws":10,"losses":6,"wins":0},"gpt-5.6-luna":{"draws":18,"losses":7,"wins":21},"gpt-5.6-sol":{"draws":5,"losses":33,"wins":4},"gpt-5.6-terra":{"draws":10,"losses":16,"wins":10},"gpt-6-astra":{"draws":2,"losses":24,"wins":0},"gpt-6-luna":{"draws":0,"losses":2,"wins":2},"gpt-6-sol":{"draws":0,"losses":3,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":16},"inclusionai/ling-3.0-flash":{"draws":6,"losses":5,"wins":13},"meituan/longcat-2.0":{"draws":11,"losses":5,"wins":18},"meta/muse-glimmer-30b":{"draws":20,"losses":8,"wins":18},"meta/muse-spark-1.2":{"draws":14,"losses":16,"wins":12},"meta/muse-spark-1.3":{"draws":13,"losses":14,"wins":9},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":15,"losses":4,"wins":13},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":24,"losses":16,"wins":6},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":12,"losses":1,"wins":9},"o3":{"draws":9,"losses":28,"wins":15},"openai/gpt-oss-120b":{"draws":14,"losses":12,"wins":14},"poolside/laguna-s-2.1":{"draws":18,"losses":5,"wins":15},"qwen/qwen3.7-max":{"draws":4,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":20,"losses":16,"wins":12},"qwen/qwen3.8-27b":{"draws":5,"losses":7,"wins":8},"qwen/qwen3.8-flash":{"draws":14,"losses":7,"wins":13},"qwen/qwen3.8-max":{"draws":11,"losses":13,"wins":22},"qwen/qwen3.8-max-0902":{"draws":7,"losses":9,"wins":2},"stealth/ox-alpha":{"draws":39,"losses":67,"wins":52},"stepfun/step-3.7-flash":{"draws":4,"losses":5,"wins":1},"tencent/hy3-preview":{"draws":3,"losses":5,"wins":4},"tencent/hy4-preview":{"draws":5,"losses":11,"wins":4},"thinkingmachines/inkling":{"draws":19,"losses":10,"wins":13},"thinkingmachines/inkling-small":{"draws":21,"losses":8,"wins":19},"x-ai/grok-4.5":{"draws":11,"losses":14,"wins":3},"x-ai/grok-4.6":{"draws":14,"losses":18,"wins":8},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":2},"x-ai/grok-build-0.1":{"draws":5,"losses":2,"wins":3},"xiaomi/mimo-v2.5":{"draws":6,"losses":0,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":20,"losses":15,"wins":19},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":15,"wins":10},"z-ai/glm-5.3-flashx":{"draws":0,"losses":0,"wins":2}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":10,"wins":8},"claude-fable-5":{"draws":2,"losses":11,"wins":1},"claude-fable-5-1":{"draws":1,"losses":19,"wins":0},"claude-opus-4-5":{"draws":43,"losses":40,"wins":19},"claude-opus-4-8":{"draws":10,"losses":38,"wins":12},"claude-opus-5":{"draws":12,"losses":88,"wins":16},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":7,"losses":10,"wins":5},"cohere/north-mini-code":{"draws":9,"losses":16,"wins":17},"deepseek/deepseek-v4-flash":{"draws":18,"losses":18,"wins":26},"deepseek/deepseek-v4-pro":{"draws":3,"losses":14,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":6,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":23,"losses":16,"wins":23},"google/gemini-3.5-flash":{"draws":5,"losses":10,"wins":7},"google/gemini-3.5-flash-lite":{"draws":26,"losses":37,"wins":17},"google/gemini-3.6-flash":{"draws":34,"losses":47,"wins":17},"google/gemini-3.8-flash":{"draws":3,"losses":13,"wins":2},"google/gemma-4-31b-it":{"draws":10,"losses":11,"wins":17},"gpt-4.1":{"draws":7,"losses":8,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":24,"losses":21,"wins":7},"gpt-5.4":{"draws":6,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":24,"losses":13,"wins":13},"gpt-5.4-nano":{"draws":7,"losses":28,"wins":17},"gpt-5.5":{"draws":14,"losses":33,"wins":15},"gpt-5.6-luna":{"draws":7,"losses":15,"wins":6},"gpt-5.6-sol":{"draws":1,"losses":10,"wins":1},"gpt-5.6-terra":{"draws":3,"losses":7,"wins":4},"gpt-6-astra":{"draws":1,"losses":19,"wins":0},"gpt-6-luna":{"draws":4,"losses":0,"wins":2},"gpt-6-sol":{"draws":2,"losses":12,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":10,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":25,"losses":24,"wins":31},"meituan/longcat-2.0":{"draws":17,"losses":21,"wins":22},"meta/muse-glimmer-30b":{"draws":7,"losses":6,"wins":7},"meta/muse-spark-1.2":{"draws":7,"losses":3,"wins":6},"meta/muse-spark-1.3":{"draws":2,"losses":6,"wins":4},"minimax/minimax-m3":{"draws":13,"losses":18,"wins":21},"mistralai/mistral-medium-3-5":{"draws":5,"losses":2,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":7,"wins":13},"moonshotai/kimi-k3":{"draws":15,"losses":23,"wins":4},"nex-agi/nex-n2-pro":{"draws":14,"losses":8,"wins":14},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":28,"losses":17,"wins":25},"o3":{"draws":7,"losses":29,"wins":16},"openai/gpt-oss-120b":{"draws":4,"losses":1,"wins":5},"poolside/laguna-s-2.1":{"draws":23,"losses":31,"wins":24},"qwen/qwen3.7-max":{"draws":22,"losses":24,"wins":10},"qwen/qwen3.7-plus":{"draws":14,"losses":18,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":5,"wins":4},"qwen/qwen3.8-27b":{"draws":1,"losses":9,"wins":2},"qwen/qwen3.8-flash":{"draws":7,"losses":4,"wins":3},"qwen/qwen3.8-max":{"draws":8,"losses":6,"wins":2},"qwen/qwen3.8-max-0902":{"draws":5,"losses":3,"wins":0},"stealth/ox-alpha":{"draws":16,"losses":37,"wins":15},"stepfun/step-3.7-flash":{"draws":5,"losses":24,"wins":15},"tencent/hy3-preview":{"draws":22,"losses":10,"wins":14},"tencent/hy4-preview":{"draws":9,"losses":12,"wins":3},"thinkingmachines/inkling":{"draws":14,"losses":9,"wins":23},"thinkingmachines/inkling-small":{"draws":2,"losses":5,"wins":5},"x-ai/grok-4.5":{"draws":25,"losses":40,"wins":13},"x-ai/grok-4.6":{"draws":5,"losses":6,"wins":1},"x-ai/grok-4.7":{"draws":0,"losses":6,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":7,"wins":10},"xiaomi/mimo-v2.5":{"draws":49,"losses":62,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":21,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":7,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":32,"losses":37,"wins":23},"z-ai/glm-5.3":{"draws":3,"losses":16,"wins":5},"z-ai/glm-5.3-flash":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.3-flashx":{"draws":5,"losses":9,"wins":2}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":18,"wins":7},"claude-fable-5":{"draws":7,"losses":15,"wins":4},"claude-fable-5-1":{"draws":3,"losses":28,"wins":1},"claude-opus-4-5":{"draws":12,"losses":23,"wins":3},"claude-opus-4-8":{"draws":2,"losses":8,"wins":0},"claude-opus-5":{"draws":3,"losses":10,"wins":1},"claude-opus-5-5":{"draws":3,"losses":7,"wins":0},"claude-sonnet-5":{"draws":20,"losses":31,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":0},"deepseek/deepseek-v4-flash":{"draws":34,"losses":25,"wins":5},"deepseek/deepseek-v4-pro":{"draws":27,"losses":19,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":17,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":5,"wins":2},"google/gemini-3.1-flash-lite":{"draws":3,"losses":1,"wins":2},"google/gemini-3.5-flash":{"draws":15,"losses":16,"wins":5},"google/gemini-3.5-flash-lite":{"draws":36,"losses":38,"wins":26},"google/gemini-3.6-flash":{"draws":24,"losses":37,"wins":18},"google/gemini-3.8-flash":{"draws":16,"losses":13,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-4.1":{"draws":2,"losses":2,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":8,"losses":4,"wins":0},"gpt-5.4":{"draws":26,"losses":6,"wins":5},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":4,"wins":0},"gpt-5.5":{"draws":0,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":22,"losses":22,"wins":10},"gpt-5.6-sol":{"draws":7,"losses":20,"wins":1},"gpt-5.6-terra":{"draws":17,"losses":28,"wins":3},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"gpt-6-luna":{"draws":2,"losses":3,"wins":1},"gpt-6-sol":{"draws":3,"losses":9,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":23,"losses":10,"wins":9},"inclusionai/ling-3.0-flash":{"draws":8,"losses":6,"wins":10},"meituan/longcat-2.0":{"draws":9,"losses":15,"wins":5},"meta/muse-glimmer-30b":{"draws":26,"losses":18,"wins":6},"meta/muse-spark-1.2":{"draws":11,"losses":14,"wins":7},"meta/muse-spark-1.3":{"draws":17,"losses":15,"wins":4},"minimax/minimax-m3":{"draws":4,"losses":2,"wins":0},"mistralai/mistral-medium-3-5":{"draws":18,"losses":8,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":16,"losses":23,"wins":5},"nex-agi/nex-n2-pro":{"draws":4,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":5,"wins":6},"o3":{"draws":21,"losses":26,"wins":14},"openai/gpt-oss-120b":{"draws":23,"losses":17,"wins":10},"poolside/laguna-s-2.1":{"draws":22,"losses":9,"wins":1},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":24,"wins":3},"qwen/qwen3.8-27b":{"draws":8,"losses":18,"wins":0},"qwen/qwen3.8-flash":{"draws":17,"losses":15,"wins":6},"qwen/qwen3.8-max":{"draws":33,"losses":35,"wins":21},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":59,"losses":58,"wins":21},"stepfun/step-3.7-flash":{"draws":5,"losses":6,"wins":5},"tencent/hy3-preview":{"draws":11,"losses":5,"wins":0},"tencent/hy4-preview":{"draws":13,"losses":21,"wins":4},"thinkingmachines/inkling":{"draws":17,"losses":10,"wins":5},"thinkingmachines/inkling-small":{"draws":29,"losses":27,"wins":14},"x-ai/grok-4.5":{"draws":12,"losses":9,"wins":4},"x-ai/grok-4.6":{"draws":15,"losses":16,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":11,"losses":4,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":9,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":21,"losses":25,"wins":8},"z-ai/glm-5.3":{"draws":6,"losses":17,"wins":1},"z-ai/glm-5.3-flash":{"draws":17,"losses":17,"wins":8},"z-ai/glm-5.3-flashx":{"draws":0,"losses":7,"wins":1}},"x-ai/grok-4.5":{"bytedance-seed/seed-2.0-code":{"draws":15,"losses":12,"wins":17},"claude-fable-5":{"draws":10,"losses":32,"wins":10},"claude-fable-5-1":{"draws":0,"losses":38,"wins":4},"claude-opus-4-5":{"draws":37,"losses":35,"wins":40},"claude-opus-4-8":{"draws":11,"losses":7,"wins":10},"claude-opus-5":{"draws":9,"losses":36,"wins":9},"claude-opus-5-5":{"draws":1,"losses":17,"wins":4},"claude-sonnet-5":{"draws":48,"losses":16,"wins":36},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":9},"deepseek/deepseek-v4-flash":{"draws":15,"losses":11,"wins":18},"deepseek/deepseek-v4-pro":{"draws":13,"losses":22,"wins":13},"deepseek/deepseek-v4-pro-0813":{"draws":17,"losses":15,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":1,"wins":5},"google/gemini-3.1-flash-lite":{"draws":1,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":18,"losses":13,"wins":15},"google/gemini-3.5-flash-lite":{"draws":89,"losses":33,"wins":100},"google/gemini-3.6-flash":{"draws":56,"losses":96,"wins":58},"google/gemini-3.8-flash":{"draws":11,"losses":16,"wins":13},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":8},"gpt-4.1":{"draws":4,"losses":2,"wins":10},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":0},"gpt-5":{"draws":4,"losses":3,"wins":5},"gpt-5.4":{"draws":18,"losses":51,"wins":21},"gpt-5.4-mini":{"draws":7,"losses":2,"wins":3},"gpt-5.4-nano":{"draws":4,"losses":8,"wins":16},"gpt-5.5":{"draws":8,"losses":4,"wins":12},"gpt-5.6-luna":{"draws":28,"losses":33,"wins":35},"gpt-5.6-sol":{"draws":11,"losses":63,"wins":28},"gpt-5.6-terra":{"draws":12,"losses":16,"wins":20},"gpt-6-astra":{"draws":3,"losses":40,"wins":3},"gpt-6-luna":{"draws":5,"losses":6,"wins":9},"gpt-6-sol":{"draws":0,"losses":10,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":20,"losses":2,"wins":16},"inclusionai/ling-3.0-flash":{"draws":21,"losses":6,"wins":21},"meituan/longcat-2.0":{"draws":21,"losses":22,"wins":39},"meta/muse-glimmer-30b":{"draws":17,"losses":5,"wins":18},"meta/muse-spark-1.2":{"draws":21,"losses":22,"wins":31},"meta/muse-spark-1.3":{"draws":4,"losses":23,"wins":11},"minimax/minimax-m3":{"draws":5,"losses":3,"wins":6},"mistralai/mistral-medium-3-5":{"draws":4,"losses":6,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":42,"losses":40,"wins":24},"nex-agi/nex-n2-pro":{"draws":6,"losses":1,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":0,"wins":2},"o3":{"draws":11,"losses":53,"wins":62},"openai/gpt-oss-120b":{"draws":21,"losses":5,"wins":12},"poolside/laguna-s-2.1":{"draws":31,"losses":19,"wins":36},"qwen/qwen3.7-max":{"draws":6,"losses":7,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":12,"wins":13},"qwen/qwen3.8-27b":{"draws":4,"losses":20,"wins":8},"qwen/qwen3.8-flash":{"draws":9,"losses":3,"wins":12},"qwen/qwen3.8-max":{"draws":22,"losses":17,"wins":18},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":5},"stealth/ox-alpha":{"draws":40,"losses":54,"wins":44},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":16},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":9},"tencent/hy4-preview":{"draws":14,"losses":25,"wins":11},"thinkingmachines/inkling":{"draws":35,"losses":11,"wins":46},"thinkingmachines/inkling-small":{"draws":21,"losses":9,"wins":23},"x-ai/grok-4.5":{"draws":18,"losses":28,"wins":8},"x-ai/grok-4.6":{"draws":19,"losses":15,"wins":12},"x-ai/grok-4.7":{"draws":0,"losses":11,"wins":3},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.5":{"draws":10,"losses":4,"wins":16},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":14,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":21,"losses":20,"wins":21},"z-ai/glm-5.3":{"draws":10,"losses":25,"wins":5},"z-ai/glm-5.3-flash":{"draws":8,"losses":23,"wins":11},"z-ai/glm-5.3-flashx":{"draws":0,"losses":2,"wins":0}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":21,"losses":8,"wins":19},"claude-fable-5":{"draws":13,"losses":32,"wins":5},"claude-fable-5-1":{"draws":2,"losses":48,"wins":2},"claude-opus-4-5":{"draws":16,"losses":13,"wins":15},"claude-opus-4-8":{"draws":7,"losses":5,"wins":2},"claude-opus-5":{"draws":3,"losses":27,"wins":2},"claude-opus-5-5":{"draws":2,"losses":12,"wins":2},"claude-sonnet-5":{"draws":24,"losses":22,"wins":14},"cohere/north-mini-code":{"draws":6,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":20,"losses":9,"wins":23},"deepseek/deepseek-v4-pro":{"draws":18,"losses":14,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":17,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":1,"wins":2},"google/gemini-3.5-flash":{"draws":18,"losses":18,"wins":14},"google/gemini-3.5-flash-lite":{"draws":40,"losses":19,"wins":31},"google/gemini-3.6-flash":{"draws":30,"losses":27,"wins":19},"google/gemini-3.8-flash":{"draws":15,"losses":22,"wins":7},"google/gemma-4-31b-it":{"draws":4,"losses":3,"wins":3},"gpt-4.1":{"draws":6,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":5,"wins":6},"gpt-5.4":{"draws":21,"losses":26,"wins":5},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":1},"gpt-5.4-nano":{"draws":4,"losses":6,"wins":4},"gpt-5.5":{"draws":6,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":22,"losses":13,"wins":23},"gpt-5.6-sol":{"draws":12,"losses":30,"wins":10},"gpt-5.6-terra":{"draws":27,"losses":11,"wins":16},"gpt-6-astra":{"draws":6,"losses":38,"wins":0},"gpt-6-luna":{"draws":2,"losses":4,"wins":4},"gpt-6-sol":{"draws":2,"losses":6,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":19,"losses":6,"wins":15},"inclusionai/ling-3.0-flash":{"draws":7,"losses":5,"wins":12},"meituan/longcat-2.0":{"draws":16,"losses":12,"wins":12},"meta/muse-glimmer-30b":{"draws":26,"losses":3,"wins":15},"meta/muse-spark-1.2":{"draws":12,"losses":9,"wins":19},"meta/muse-spark-1.3":{"draws":14,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":17,"losses":3,"wins":8},"moonshotai/kimi-k3":{"draws":11,"losses":17,"wins":18},"nex-agi/nex-n2-pro":{"draws":5,"losses":1,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":6},"o3":{"draws":15,"losses":28,"wins":27},"openai/gpt-oss-120b":{"draws":21,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":20,"losses":9,"wins":11},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.7-plus":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":23,"losses":17,"wins":10},"qwen/qwen3.8-27b":{"draws":10,"losses":13,"wins":3},"qwen/qwen3.8-flash":{"draws":12,"losses":6,"wins":8},"qwen/qwen3.8-max":{"draws":25,"losses":20,"wins":11},"qwen/qwen3.8-max-0902":{"draws":7,"losses":5,"wins":0},"stealth/ox-alpha":{"draws":57,"losses":74,"wins":23},"stepfun/step-3.7-flash":{"draws":5,"losses":5,"wins":10},"tencent/hy3-preview":{"draws":5,"losses":1,"wins":4},"tencent/hy4-preview":{"draws":19,"losses":19,"wins":12},"thinkingmachines/inkling":{"draws":12,"losses":3,"wins":15},"thinkingmachines/inkling-small":{"draws":25,"losses":11,"wins":18},"x-ai/grok-4.5":{"draws":15,"losses":27,"wins":6},"x-ai/grok-4.6":{"draws":11,"losses":17,"wins":2},"x-ai/grok-4.7":{"draws":2,"losses":6,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":2,"wins":0},"xiaomi/mimo-v2.5":{"draws":12,"losses":5,"wins":13},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":3,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":0},"z-ai/glm-5.2":{"draws":22,"losses":16,"wins":24},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":6},"z-ai/glm-5.3-flash":{"draws":9,"losses":26,"wins":13},"z-ai/glm-5.3-flashx":{"draws":8,"losses":3,"wins":1}},"x-ai/grok-4.7":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":6,"wins":2},"claude-fable-5":{"draws":0,"losses":6,"wins":6},"claude-fable-5-1":{"draws":1,"losses":7,"wins":0},"claude-opus-4-5":{"draws":3,"losses":5,"wins":4},"claude-opus-4-8":{"draws":4,"losses":2,"wins":4},"claude-opus-5":{"draws":3,"losses":8,"wins":3},"claude-opus-5-5":{"draws":5,"losses":32,"wins":5},"claude-sonnet-5":{"draws":2,"losses":3,"wins":5},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":3,"wins":0},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":4},"google/gemini-3.5-flash-lite":{"draws":2,"losses":8,"wins":4},"google/gemini-3.6-flash":{"draws":1,"losses":6,"wins":3},"google/gemini-3.8-flash":{"draws":2,"losses":6,"wins":2},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":2,"wins":0},"gpt-5.4":{"draws":2,"losses":3,"wins":5},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":6,"losses":1,"wins":7},"gpt-5.5":{"draws":1,"losses":7,"wins":4},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":3},"gpt-5.6-terra":{"draws":3,"losses":3,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":7,"losses":14,"wins":17},"gpt-6-sol":{"draws":9,"losses":25,"wins":8},"inception/mercury-2.5-preview":{"draws":1,"losses":1,"wins":2},"inclusionai/ling-3.0-flash":{"draws":4,"losses":1,"wins":3},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":9},"meta/muse-spark-1.2":{"draws":0,"losses":4,"wins":0},"meta/muse-spark-1.3":{"draws":3,"losses":3,"wins":4},"minimax/minimax-m3":{"draws":1,"losses":0,"wins":1},"mistralai/mistral-medium-3-5":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":0,"wins":1},"moonshotai/kimi-k3":{"draws":3,"losses":0,"wins":1},"nex-agi/nex-n2-pro":{"draws":0,"losses":0,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":2},"o3":{"draws":2,"losses":3,"wins":5},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":4},"poolside/laguna-s-2.1":{"draws":0,"losses":3,"wins":3},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":3,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":0},"qwen/qwen3.8-flash":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-max":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-max-0902":{"draws":7,"losses":0,"wins":1},"stealth/ox-alpha":{"draws":4,"losses":5,"wins":5},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":7},"tencent/hy4-preview":{"draws":0,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":0},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.6":{"draws":1,"losses":4,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":12,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":2,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":9},"z-ai/glm-5.2":{"draws":3,"losses":5,"wins":8},"z-ai/glm-5.3":{"draws":3,"losses":7,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":2,"wins":8},"z-ai/glm-5.3-flashx":{"draws":6,"losses":14,"wins":10}},"xiaomi/mimo-v2.5":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":8,"wins":7},"claude-fable-5":{"draws":0,"losses":20,"wins":0},"claude-fable-5-1":{"draws":1,"losses":33,"wins":0},"claude-opus-4-5":{"draws":45,"losses":57,"wins":38},"claude-opus-4-8":{"draws":29,"losses":69,"wins":8},"claude-opus-5":{"draws":20,"losses":90,"wins":4},"claude-opus-5-5":{"draws":3,"losses":17,"wins":0},"claude-sonnet-5":{"draws":10,"losses":19,"wins":1},"cohere/north-mini-code":{"draws":23,"losses":10,"wins":19},"deepseek/deepseek-v4-flash":{"draws":35,"losses":30,"wins":43},"deepseek/deepseek-v4-pro":{"draws":2,"losses":8,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":13,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":12,"losses":13,"wins":1},"google/gemini-3.1-flash-lite":{"draws":21,"losses":24,"wins":33},"google/gemini-3.5-flash":{"draws":3,"losses":15,"wins":6},"google/gemini-3.5-flash-lite":{"draws":14,"losses":23,"wins":15},"google/gemini-3.6-flash":{"draws":22,"losses":45,"wins":17},"google/gemini-3.8-flash":{"draws":6,"losses":13,"wins":3},"google/gemma-4-31b-it":{"draws":16,"losses":28,"wins":32},"gpt-4.1":{"draws":20,"losses":22,"wins":12},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":24,"losses":21,"wins":9},"gpt-5.4":{"draws":6,"losses":10,"wins":0},"gpt-5.4-mini":{"draws":29,"losses":24,"wins":25},"gpt-5.4-nano":{"draws":25,"losses":60,"wins":53},"gpt-5.5":{"draws":35,"losses":35,"wins":12},"gpt-5.6-luna":{"draws":22,"losses":8,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":17,"wins":1},"gpt-5.6-terra":{"draws":7,"losses":23,"wins":2},"gpt-6-astra":{"draws":1,"losses":25,"wins":0},"gpt-6-luna":{"draws":9,"losses":3,"wins":4},"gpt-6-sol":{"draws":5,"losses":16,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":3,"losses":3,"wins":8},"inclusionai/ling-3.0-flash":{"draws":28,"losses":14,"wins":28},"meituan/longcat-2.0":{"draws":24,"losses":33,"wins":27},"meta/muse-glimmer-30b":{"draws":18,"losses":10,"wins":6},"meta/muse-spark-1.2":{"draws":4,"losses":13,"wins":3},"meta/muse-spark-1.3":{"draws":9,"losses":19,"wins":4},"minimax/minimax-m3":{"draws":21,"losses":22,"wins":33},"mistralai/mistral-medium-3-5":{"draws":2,"losses":9,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":16,"wins":6},"moonshotai/kimi-k3":{"draws":11,"losses":42,"wins":9},"nex-agi/nex-n2-pro":{"draws":13,"losses":18,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":37,"wins":39},"o3":{"draws":10,"losses":34,"wins":14},"openai/gpt-oss-120b":{"draws":7,"losses":8,"wins":5},"poolside/laguna-s-2.1":{"draws":16,"losses":32,"wins":18},"qwen/qwen3.7-max":{"draws":20,"losses":33,"wins":13},"qwen/qwen3.7-plus":{"draws":7,"losses":19,"wins":26},"qwen/qwen3.8-2.4t-a95b":{"draws":12,"losses":12,"wins":6},"qwen/qwen3.8-27b":{"draws":1,"losses":13,"wins":2},"qwen/qwen3.8-flash":{"draws":4,"losses":9,"wins":3},"qwen/qwen3.8-max":{"draws":13,"losses":16,"wins":5},"qwen/qwen3.8-max-0902":{"draws":14,"losses":9,"wins":1},"stealth/ox-alpha":{"draws":17,"losses":59,"wins":16},"stepfun/step-3.7-flash":{"draws":18,"losses":21,"wins":25},"tencent/hy3-preview":{"draws":16,"losses":27,"wins":17},"tencent/hy4-preview":{"draws":2,"losses":30,"wins":2},"thinkingmachines/inkling":{"draws":15,"losses":27,"wins":42},"thinkingmachines/inkling-small":{"draws":11,"losses":10,"wins":7},"x-ai/grok-4.5":{"draws":12,"losses":24,"wins":8},"x-ai/grok-4.6":{"draws":12,"losses":17,"wins":3},"x-ai/grok-4.7":{"draws":1,"losses":7,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":22,"wins":10},"xiaomi/mimo-v2.5":{"draws":65,"losses":52,"wins":73},"xiaomi/mimo-v2.5-pro":{"draws":15,"losses":32,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":15,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":37,"losses":53,"wins":28},"z-ai/glm-5.3":{"draws":6,"losses":14,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":14,"wins":6},"z-ai/glm-5.3-flashx":{"draws":4,"losses":8,"wins":2}},"xiaomi/mimo-v2.5-pro":{"bytedance-seed/seed-2.0-code":{"draws":9,"losses":3,"wins":4},"claude-fable-5":{"draws":0,"losses":8,"wins":0},"claude-fable-5-1":{"draws":0,"losses":12,"wins":0},"claude-opus-4-5":{"draws":12,"losses":22,"wins":16},"claude-opus-4-8":{"draws":11,"losses":9,"wins":10},"claude-opus-5":{"draws":4,"losses":53,"wins":3},"claude-opus-5-5":{"draws":0,"losses":6,"wins":0},"claude-sonnet-5":{"draws":1,"losses":5,"wins":4},"cohere/north-mini-code":{"draws":10,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":18,"losses":13,"wins":13},"deepseek/deepseek-v4-pro":{"draws":7,"losses":10,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":6,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":5,"wins":0},"google/gemini-3.1-flash-lite":{"draws":7,"losses":0,"wins":15},"google/gemini-3.5-flash":{"draws":4,"losses":7,"wins":5},"google/gemini-3.5-flash-lite":{"draws":9,"losses":13,"wins":8},"google/gemini-3.6-flash":{"draws":12,"losses":15,"wins":7},"google/gemini-3.8-flash":{"draws":7,"losses":10,"wins":3},"google/gemma-4-31b-it":{"draws":2,"losses":6,"wins":12},"gpt-4.1":{"draws":4,"losses":9,"wins":5},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":10,"losses":12,"wins":10},"gpt-5.4":{"draws":6,"losses":12,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":13,"wins":10},"gpt-5.4-nano":{"draws":20,"losses":11,"wins":21},"gpt-5.5":{"draws":14,"losses":14,"wins":12},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":5,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":4,"wins":0},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":4,"losses":2,"wins":0},"gpt-6-sol":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":4,"losses":5,"wins":3},"inclusionai/ling-3.0-flash":{"draws":17,"losses":12,"wins":15},"meituan/longcat-2.0":{"draws":21,"losses":17,"wins":16},"meta/muse-glimmer-30b":{"draws":4,"losses":3,"wins":7},"meta/muse-spark-1.2":{"draws":5,"losses":12,"wins":3},"meta/muse-spark-1.3":{"draws":0,"losses":11,"wins":1},"minimax/minimax-m3":{"draws":7,"losses":8,"wins":13},"mistralai/mistral-medium-3-5":{"draws":6,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":9,"losses":10,"wins":7},"nex-agi/nex-n2-pro":{"draws":8,"losses":6,"wins":10},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":16,"losses":8,"wins":10},"o3":{"draws":9,"losses":10,"wins":9},"openai/gpt-oss-120b":{"draws":6,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":13,"losses":13,"wins":14},"qwen/qwen3.7-max":{"draws":8,"losses":13,"wins":7},"qwen/qwen3.7-plus":{"draws":14,"losses":4,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":10,"wins":2},"qwen/qwen3.8-27b":{"draws":7,"losses":9,"wins":0},"qwen/qwen3.8-flash":{"draws":3,"losses":8,"wins":1},"qwen/qwen3.8-max":{"draws":3,"losses":6,"wins":5},"qwen/qwen3.8-max-0902":{"draws":3,"losses":3,"wins":2},"stealth/ox-alpha":{"draws":11,"losses":29,"wins":8},"stepfun/step-3.7-flash":{"draws":10,"losses":9,"wins":11},"tencent/hy3-preview":{"draws":9,"losses":13,"wins":6},"tencent/hy4-preview":{"draws":0,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":5,"losses":10,"wins":19},"thinkingmachines/inkling-small":{"draws":8,"losses":2,"wins":6},"x-ai/grok-4.5":{"draws":4,"losses":16,"wins":4},"x-ai/grok-4.6":{"draws":3,"losses":11,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":4,"wins":0},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":4},"xiaomi/mimo-v2.5":{"draws":26,"losses":24,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":6,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":22,"losses":25,"wins":17},"z-ai/glm-5.3":{"draws":5,"losses":12,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":9,"wins":3},"z-ai/glm-5.3-flashx":{"draws":3,"losses":5,"wins":0}},"xiaomi/mimo-v2.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":3,"wins":1},"claude-fable-5":{"draws":2,"losses":4,"wins":0},"claude-fable-5-1":{"draws":1,"losses":11,"wins":0},"claude-opus-4-5":{"draws":3,"losses":4,"wins":1},"claude-opus-4-8":{"draws":2,"losses":0,"wins":2},"claude-opus-5":{"draws":1,"losses":7,"wins":0},"claude-opus-5-5":{"draws":4,"losses":42,"wins":0},"claude-sonnet-5":{"draws":5,"losses":1,"wins":6},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":5},"deepseek/deepseek-v4-flash":{"draws":10,"losses":2,"wins":6},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":3,"wins":1},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":5,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":3,"losses":1,"wins":4},"google/gemini-3.5-flash-lite":{"draws":3,"losses":2,"wins":5},"google/gemini-3.6-flash":{"draws":1,"losses":6,"wins":7},"google/gemini-3.8-flash":{"draws":1,"losses":4,"wins":1},"google/gemma-4-31b-it":{"draws":0,"losses":1,"wins":1},"gpt-4.1":{"draws":4,"losses":0,"wins":2},"gpt-5":{"draws":4,"losses":0,"wins":0},"gpt-5.4":{"draws":0,"losses":4,"wins":2},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":7,"losses":0,"wins":3},"gpt-5.5":{"draws":2,"losses":2,"wins":2},"gpt-5.6-luna":{"draws":7,"losses":3,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":3,"wins":1},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":2},"gpt-6-luna":{"draws":11,"losses":19,"wins":10},"gpt-6-sol":{"draws":4,"losses":31,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":1,"losses":1,"wins":0},"meta/muse-glimmer-30b":{"draws":1,"losses":3,"wins":2},"meta/muse-spark-1.2":{"draws":0,"losses":3,"wins":1},"meta/muse-spark-1.3":{"draws":4,"losses":5,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":1,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":4,"losses":0,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":4,"wins":3},"o3":{"draws":3,"losses":6,"wins":13},"openai/gpt-oss-120b":{"draws":3,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":3,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":6,"wins":0},"qwen/qwen3.8-27b":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.8-flash":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":5},"qwen/qwen3.8-max-0902":{"draws":6,"losses":8,"wins":8},"stealth/ox-alpha":{"draws":6,"losses":13,"wins":9},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":2,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":2,"losses":0,"wins":6},"thinkingmachines/inkling-small":{"draws":5,"losses":1,"wins":6},"x-ai/grok-4.5":{"draws":0,"losses":4,"wins":0},"x-ai/grok-4.6":{"draws":1,"losses":5,"wins":0},"x-ai/grok-4.7":{"draws":2,"losses":14,"wins":4},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":5,"losses":1,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":7,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":10,"wins":4},"z-ai/glm-5.2":{"draws":5,"losses":5,"wins":0},"z-ai/glm-5.3":{"draws":3,"losses":9,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":0,"wins":0},"z-ai/glm-5.3-flashx":{"draws":11,"losses":17,"wins":8}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":5,"wins":5},"claude-fable-5":{"draws":0,"losses":12,"wins":0},"claude-fable-5-1":{"draws":1,"losses":9,"wins":2},"claude-opus-4-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-8":{"draws":0,"losses":8,"wins":4},"claude-opus-5":{"draws":3,"losses":6,"wins":1},"claude-opus-5-5":{"draws":6,"losses":41,"wins":5},"claude-sonnet-5":{"draws":5,"losses":4,"wins":3},"cohere/north-mini-code":{"draws":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":3,"losses":1,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":1,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":4,"wins":9},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":4,"losses":3,"wins":5},"google/gemini-3.5-flash-lite":{"draws":0,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":4,"losses":10,"wins":2},"google/gemini-3.8-flash":{"draws":2,"losses":1,"wins":5},"google/gemma-4-31b-it":{"draws":0,"losses":2,"wins":0},"gpt-4.1":{"draws":4,"losses":1,"wins":3},"gpt-5":{"draws":2,"losses":0,"wins":2},"gpt-5.4":{"draws":2,"losses":7,"wins":1},"gpt-5.4-mini":{"draws":0,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":4,"losses":0,"wins":6},"gpt-5.5":{"draws":1,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":1,"losses":4,"wins":3},"gpt-5.6-sol":{"draws":3,"losses":4,"wins":1},"gpt-5.6-terra":{"draws":4,"losses":6,"wins":2},"gpt-6-astra":{"draws":0,"losses":6,"wins":0},"gpt-6-luna":{"draws":11,"losses":14,"wins":21},"gpt-6-sol":{"draws":10,"losses":33,"wins":5},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":2,"losses":0,"wins":2},"meituan/longcat-2.0":{"draws":8,"losses":0,"wins":4},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":2},"meta/muse-spark-1.2":{"draws":1,"losses":1,"wins":2},"meta/muse-spark-1.3":{"draws":1,"losses":4,"wins":3},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":0,"losses":2,"wins":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":6},"o3":{"draws":0,"losses":5,"wins":3},"openai/gpt-oss-120b":{"draws":1,"losses":1,"wins":0},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-max":{"draws":1,"losses":1,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":4,"wins":4},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":2,"losses":4,"wins":2},"qwen/qwen3.8-max":{"draws":6,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":13,"wins":12},"stealth/ox-alpha":{"draws":6,"losses":11,"wins":9},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":2,"losses":4,"wins":4},"thinkingmachines/inkling":{"draws":5,"losses":0,"wins":1},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":6},"x-ai/grok-4.5":{"draws":0,"losses":5,"wins":5},"x-ai/grok-4.6":{"draws":5,"losses":7,"wins":4},"x-ai/grok-4.7":{"draws":5,"losses":23,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":4,"losses":1,"wins":7},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":9,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":3,"wins":0},"z-ai/glm-5.2":{"draws":4,"losses":6,"wins":2},"z-ai/glm-5.3":{"draws":2,"losses":8,"wins":2},"z-ai/glm-5.3-flash":{"draws":3,"losses":3,"wins":0},"z-ai/glm-5.3-flashx":{"draws":9,"losses":21,"wins":14}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":37,"losses":26,"wins":19},"claude-fable-5":{"draws":17,"losses":31,"wins":6},"claude-fable-5-1":{"draws":6,"losses":39,"wins":1},"claude-opus-4-5":{"draws":66,"losses":88,"wins":44},"claude-opus-4-8":{"draws":30,"losses":52,"wins":26},"claude-opus-5":{"draws":34,"losses":105,"wins":19},"claude-opus-5-5":{"draws":2,"losses":26,"wins":0},"claude-sonnet-5":{"draws":32,"losses":40,"wins":14},"cohere/north-mini-code":{"draws":6,"losses":3,"wins":27},"deepseek/deepseek-v4-flash":{"draws":41,"losses":30,"wins":51},"deepseek/deepseek-v4-pro":{"draws":22,"losses":33,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":29,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":14,"wins":9},"google/gemini-3.1-flash-lite":{"draws":23,"losses":14,"wins":49},"google/gemini-3.5-flash":{"draws":25,"losses":31,"wins":28},"google/gemini-3.5-flash-lite":{"draws":58,"losses":74,"wins":52},"google/gemini-3.6-flash":{"draws":51,"losses":53,"wins":30},"google/gemini-3.8-flash":{"draws":22,"losses":36,"wins":12},"google/gemma-4-31b-it":{"draws":14,"losses":8,"wins":16},"gpt-4.1":{"draws":10,"losses":12,"wins":16},"gpt-4.1-nano":{"draws":0,"losses":2,"wins":0},"gpt-5":{"draws":24,"losses":26,"wins":28},"gpt-5.4":{"draws":29,"losses":25,"wins":16},"gpt-5.4-mini":{"draws":32,"losses":13,"wins":31},"gpt-5.4-nano":{"draws":29,"losses":36,"wins":41},"gpt-5.5":{"draws":42,"losses":42,"wins":22},"gpt-5.6-luna":{"draws":28,"losses":17,"wins":27},"gpt-5.6-sol":{"draws":4,"losses":52,"wins":8},"gpt-5.6-terra":{"draws":30,"losses":31,"wins":15},"gpt-6-astra":{"draws":1,"losses":45,"wins":0},"gpt-6-luna":{"draws":5,"losses":9,"wins":6},"gpt-6-sol":{"draws":2,"losses":16,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":30,"losses":7,"wins":31},"inclusionai/ling-3.0-flash":{"draws":34,"losses":11,"wins":13},"meituan/longcat-2.0":{"draws":43,"losses":31,"wins":54},"meta/muse-glimmer-30b":{"draws":36,"losses":13,"wins":23},"meta/muse-spark-1.2":{"draws":19,"losses":28,"wins":23},"meta/muse-spark-1.3":{"draws":14,"losses":19,"wins":9},"minimax/minimax-m3":{"draws":20,"losses":12,"wins":20},"mistralai/mistral-medium-3-5":{"draws":30,"losses":7,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":13,"wins":11},"moonshotai/kimi-k3":{"draws":27,"losses":27,"wins":16},"nex-agi/nex-n2-pro":{"draws":21,"losses":12,"wins":15},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":46,"losses":19,"wins":25},"o3":{"draws":14,"losses":48,"wins":36},"openai/gpt-oss-120b":{"draws":33,"losses":18,"wins":23},"poolside/laguna-s-2.1":{"draws":57,"losses":34,"wins":27},"qwen/qwen3.7-max":{"draws":28,"losses":22,"wins":28},"qwen/qwen3.7-plus":{"draws":30,"losses":12,"wins":20},"qwen/qwen3.8-2.4t-a95b":{"draws":31,"losses":31,"wins":20},"qwen/qwen3.8-27b":{"draws":16,"losses":20,"wins":12},"qwen/qwen3.8-flash":{"draws":18,"losses":17,"wins":11},"qwen/qwen3.8-max":{"draws":23,"losses":20,"wins":17},"qwen/qwen3.8-max-0902":{"draws":6,"losses":15,"wins":5},"stealth/ox-alpha":{"draws":60,"losses":106,"wins":52},"stepfun/step-3.7-flash":{"draws":17,"losses":12,"wins":17},"tencent/hy3-preview":{"draws":22,"losses":13,"wins":23},"tencent/hy4-preview":{"draws":19,"losses":29,"wins":14},"thinkingmachines/inkling":{"draws":36,"losses":31,"wins":37},"thinkingmachines/inkling-small":{"draws":40,"losses":22,"wins":26},"x-ai/grok-4.5":{"draws":26,"losses":50,"wins":16},"x-ai/grok-4.6":{"draws":19,"losses":31,"wins":6},"x-ai/grok-4.7":{"draws":1,"losses":10,"wins":3},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":15},"xiaomi/mimo-v2.5":{"draws":63,"losses":40,"wins":65},"xiaomi/mimo-v2.5-pro":{"draws":25,"losses":24,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":8,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":56,"losses":51,"wins":43},"z-ai/glm-5.3":{"draws":20,"losses":42,"wins":4},"z-ai/glm-5.3-flash":{"draws":25,"losses":31,"wins":14},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":6}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":10,"wins":17},"claude-fable-5":{"draws":9,"losses":29,"wins":16},"claude-fable-5-1":{"draws":2,"losses":48,"wins":2},"claude-opus-4-5":{"draws":17,"losses":11,"wins":16},"claude-opus-4-8":{"draws":4,"losses":9,"wins":5},"claude-opus-5":{"draws":2,"losses":19,"wins":3},"claude-opus-5-5":{"draws":1,"losses":9,"wins":0},"claude-sonnet-5":{"draws":20,"losses":10,"wins":24},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-flash":{"draws":27,"losses":7,"wins":16},"deepseek/deepseek-v4-pro":{"draws":16,"losses":12,"wins":14},"deepseek/deepseek-v4-pro-0813":{"draws":12,"losses":16,"wins":12},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"wins":5},"google/gemini-3.5-flash":{"draws":16,"losses":20,"wins":14},"google/gemini-3.5-flash-lite":{"draws":31,"losses":14,"wins":47},"google/gemini-3.6-flash":{"draws":20,"losses":25,"wins":23},"google/gemini-3.8-flash":{"draws":11,"losses":24,"wins":15},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":3,"wins":11},"gpt-5.4":{"draws":20,"losses":32,"wins":12},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":9},"gpt-5.5":{"draws":4,"losses":3,"wins":7},"gpt-5.6-luna":{"draws":26,"losses":15,"wins":15},"gpt-5.6-sol":{"draws":9,"losses":28,"wins":7},"gpt-5.6-terra":{"draws":20,"losses":12,"wins":16},"gpt-6-astra":{"draws":7,"losses":45,"wins":2},"gpt-6-luna":{"draws":3,"losses":3,"wins":0},"gpt-6-sol":{"draws":2,"losses":3,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":18,"losses":4,"wins":16},"inclusionai/ling-3.0-flash":{"draws":12,"losses":0,"wins":8},"meituan/longcat-2.0":{"draws":14,"losses":5,"wins":15},"meta/muse-glimmer-30b":{"draws":15,"losses":10,"wins":13},"meta/muse-spark-1.2":{"draws":7,"losses":14,"wins":7},"meta/muse-spark-1.3":{"draws":13,"losses":19,"wins":10},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":17,"losses":7,"wins":10},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":21,"losses":12,"wins":15},"nex-agi/nex-n2-pro":{"draws":1,"losses":0,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":5,"wins":5},"o3":{"draws":6,"losses":22,"wins":24},"openai/gpt-oss-120b":{"draws":22,"losses":5,"wins":21},"poolside/laguna-s-2.1":{"draws":14,"losses":5,"wins":13},"qwen/qwen3.7-max":{"draws":4,"losses":4,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":8,"wins":16},"qwen/qwen3.8-27b":{"draws":6,"losses":5,"wins":11},"qwen/qwen3.8-flash":{"draws":15,"losses":9,"wins":8},"qwen/qwen3.8-max":{"draws":18,"losses":19,"wins":11},"qwen/qwen3.8-max-0902":{"draws":5,"losses":1,"wins":4},"stealth/ox-alpha":{"draws":46,"losses":63,"wins":42},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":3},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":4},"tencent/hy4-preview":{"draws":15,"losses":12,"wins":19},"thinkingmachines/inkling":{"draws":12,"losses":7,"wins":17},"thinkingmachines/inkling-small":{"draws":17,"losses":12,"wins":23},"x-ai/grok-4.5":{"draws":14,"losses":7,"wins":17},"x-ai/grok-4.6":{"draws":14,"losses":25,"wins":11},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":3},"xiaomi/mimo-v2.5":{"draws":10,"losses":0,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":4,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":25,"losses":12,"wins":17},"z-ai/glm-5.3":{"draws":5,"losses":23,"wins":0},"z-ai/glm-5.3-flash":{"draws":13,"losses":17,"wins":16},"z-ai/glm-5.3-flashx":{"draws":3,"losses":2,"wins":1}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":4,"wins":24},"claude-fable-5":{"draws":10,"losses":28,"wins":6},"claude-fable-5-1":{"draws":2,"losses":47,"wins":3},"claude-opus-4-5":{"draws":14,"losses":22,"wins":22},"claude-opus-4-8":{"draws":5,"losses":4,"wins":1},"claude-opus-5":{"draws":5,"losses":19,"wins":6},"claude-opus-5-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":16,"losses":18,"wins":18},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":25,"losses":12,"wins":13},"deepseek/deepseek-v4-pro":{"draws":16,"losses":10,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":20,"wins":17},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":7,"wins":0},"google/gemini-3.1-flash-lite":{"draws":1,"losses":1,"wins":6},"google/gemini-3.5-flash":{"draws":16,"losses":24,"wins":14},"google/gemini-3.5-flash-lite":{"draws":30,"losses":30,"wins":26},"google/gemini-3.6-flash":{"draws":27,"losses":33,"wins":20},"google/gemini-3.8-flash":{"draws":15,"losses":22,"wins":11},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":4},"gpt-4.1":{"draws":1,"losses":0,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":0},"gpt-5":{"draws":7,"losses":4,"wins":11},"gpt-5.4":{"draws":11,"losses":18,"wins":15},"gpt-5.4-mini":{"draws":5,"losses":2,"wins":3},"gpt-5.4-nano":{"draws":2,"losses":1,"wins":5},"gpt-5.5":{"draws":6,"losses":5,"wins":5},"gpt-5.6-luna":{"draws":21,"losses":15,"wins":12},"gpt-5.6-sol":{"draws":15,"losses":28,"wins":9},"gpt-5.6-terra":{"draws":13,"losses":10,"wins":13},"gpt-6-astra":{"draws":8,"losses":33,"wins":3},"gpt-6-luna":{"draws":2,"losses":3,"wins":3},"gpt-6-sol":{"draws":1,"losses":0,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":12,"losses":3,"wins":17},"inclusionai/ling-3.0-flash":{"draws":4,"losses":2,"wins":10},"meituan/longcat-2.0":{"draws":10,"losses":13,"wins":17},"meta/muse-glimmer-30b":{"draws":20,"losses":8,"wins":18},"meta/muse-spark-1.2":{"draws":8,"losses":11,"wins":11},"meta/muse-spark-1.3":{"draws":11,"losses":19,"wins":10},"minimax/minimax-m3":{"draws":3,"losses":1,"wins":4},"mistralai/mistral-medium-3-5":{"draws":9,"losses":7,"wins":14},"moonshotai/kimi-k3":{"draws":21,"losses":12,"wins":9},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":3,"wins":5},"o3":{"draws":10,"losses":20,"wins":18},"openai/gpt-oss-120b":{"draws":12,"losses":6,"wins":14},"poolside/laguna-s-2.1":{"draws":14,"losses":8,"wins":6},"qwen/qwen3.7-max":{"draws":2,"losses":4,"wins":0},"qwen/qwen3.7-plus":{"draws":2,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":16,"wins":10},"qwen/qwen3.8-27b":{"draws":14,"losses":10,"wins":4},"qwen/qwen3.8-flash":{"draws":13,"losses":11,"wins":4},"qwen/qwen3.8-max":{"draws":18,"losses":15,"wins":13},"qwen/qwen3.8-max-0902":{"draws":1,"losses":6,"wins":1},"stealth/ox-alpha":{"draws":50,"losses":77,"wins":35},"stepfun/step-3.7-flash":{"draws":7,"losses":2,"wins":9},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":3},"tencent/hy4-preview":{"draws":15,"losses":16,"wins":9},"thinkingmachines/inkling":{"draws":16,"losses":8,"wins":12},"thinkingmachines/inkling-small":{"draws":20,"losses":14,"wins":22},"x-ai/grok-4.5":{"draws":7,"losses":8,"wins":9},"x-ai/grok-4.6":{"draws":16,"losses":12,"wins":12},"x-ai/grok-4.7":{"draws":0,"losses":3,"wins":1},"x-ai/grok-build-0.1":{"draws":3,"losses":1,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":8,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":2,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":25,"losses":14,"wins":23},"z-ai/glm-5.3":{"draws":8,"losses":23,"wins":5},"z-ai/glm-5.3-flash":{"draws":11,"losses":14,"wins":5},"z-ai/glm-5.3-flashx":{"draws":1,"losses":1,"wins":2}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":1,"wins":3},"claude-fable-5":{"draws":1,"losses":5,"wins":2},"claude-fable-5-1":{"draws":0,"losses":19,"wins":1},"claude-opus-4-5":{"draws":4,"losses":0,"wins":2},"claude-opus-4-8":{"draws":2,"losses":6,"wins":2},"claude-opus-5":{"draws":2,"losses":5,"wins":1},"claude-opus-5-5":{"draws":4,"losses":47,"wins":1},"claude-sonnet-5":{"draws":4,"losses":0,"wins":0},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":1,"losses":1,"wins":8},"deepseek/deepseek-v4-pro":{"draws":0,"losses":2,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":0,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":5,"wins":4},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":11},"google/gemini-3.5-flash":{"draws":5,"losses":3,"wins":2},"google/gemini-3.5-flash-lite":{"draws":2,"losses":1,"wins":5},"google/gemini-3.6-flash":{"draws":3,"losses":8,"wins":1},"google/gemini-3.8-flash":{"draws":0,"losses":1,"wins":3},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1":{"draws":4,"losses":0,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":3,"losses":1,"wins":0},"gpt-5.4":{"draws":2,"losses":2,"wins":2},"gpt-5.4-mini":{"draws":0,"losses":3,"wins":7},"gpt-5.4-nano":{"draws":3,"losses":5,"wins":6},"gpt-5.5":{"draws":4,"losses":2,"wins":0},"gpt-5.6-luna":{"draws":2,"losses":3,"wins":7},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":3},"gpt-5.6-terra":{"draws":2,"losses":5,"wins":1},"gpt-6-astra":{"draws":1,"losses":5,"wins":0},"gpt-6-luna":{"draws":13,"losses":14,"wins":19},"gpt-6-sol":{"draws":9,"losses":29,"wins":10},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":2},"inclusionai/ling-3.0-flash":{"draws":3,"losses":2,"wins":3},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":2},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":1},"meta/muse-spark-1.2":{"draws":2,"losses":2,"wins":2},"meta/muse-spark-1.3":{"draws":6,"losses":0,"wins":2},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"mistralai/mistral-medium-3-5":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":0,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":2,"wins":0},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":1,"wins":3},"o3":{"draws":1,"losses":2,"wins":11},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":1},"poolside/laguna-s-2.1":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":3,"wins":7},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":3},"qwen/qwen3.8-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.8-max-0902":{"draws":9,"losses":9,"wins":4},"stealth/ox-alpha":{"draws":5,"losses":17,"wins":12},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":2},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":0,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":6,"losses":0,"wins":8},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":4},"x-ai/grok-4.5":{"draws":2,"losses":3,"wins":3},"x-ai/grok-4.6":{"draws":6,"losses":4,"wins":0},"x-ai/grok-4.7":{"draws":5,"losses":15,"wins":8},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":6,"losses":0,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":10,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":11,"wins":6},"z-ai/glm-5.2":{"draws":4,"losses":2,"wins":6},"z-ai/glm-5.3":{"draws":3,"losses":9,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":5,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":12,"wins":8}}}}}