{"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":"2026-09-25T16:39:35Z","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":1.9134900000000001}},"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":15.613270000000004},"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":84.3084541142194,"highest":94.27795884318934,"medium":81.66546467894545,"none":76.98193882052338},"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":"2026-09-25T14:34:00Z","match_totals_all":{"draws":552,"losses":454,"wins":4834},"match_totals_tracks":{"highest":{"draws":63,"losses":82,"wins":1771},"medium":{"draws":204,"losses":161,"wins":1597},"none":{"draws":285,"losses":211,"wins":1466}},"model_slug":"gpt-6-astra","overall":{"max":100.0,"mean":84.30845411421939,"min":50.02617127882385},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":1,"overall_ranking_status":"ranked","per_game":{"GB2-01":93.77364643873946,"GB2-02":100.0,"GB2-03":100.0,"GB2-04":97.3475278073704,"GB2-05":99.99999999999999,"GB2-06":83.44269781880206,"GB2-07":99.65604153579027,"GB2-08":80.00375714481252},"per_game_all":{"GB2-01":79.92201724111771,"GB2-02":71.31157920031018,"GB2-03":80.17946695290689,"GB2-04":92.8382338415909,"GB2-05":94.06683430648089,"GB2-06":80.55628047276433,"GB2-07":97.33336427670851,"GB2-08":78.25985662187577},"per_game_match_totals_all":{"GB2-01":{"draws":32,"losses":85,"wins":597},"GB2-02":{"draws":210,"losses":31,"wins":479},"GB2-03":{"draws":180,"losses":32,"wins":502},"GB2-04":{"draws":67,"losses":50,"wins":585},"GB2-05":{"draws":0,"losses":21,"wins":667},"GB2-06":{"draws":63,"losses":91,"wins":570},"GB2-07":{"draws":0,"losses":22,"wins":770},"GB2-08":{"draws":0,"losses":122,"wins":664}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":7,"wins":211},"GB2-02":{"draws":12,"losses":3,"wins":219},"GB2-03":{"draws":8,"losses":1,"wins":227},"GB2-04":{"draws":18,"losses":8,"wins":208},"GB2-05":{"draws":0,"losses":0,"wins":236},"GB2-06":{"draws":25,"losses":23,"wins":190},"GB2-07":{"draws":0,"losses":4,"wins":250},"GB2-08":{"draws":0,"losses":36,"wins":230}},"medium":{"GB2-01":{"draws":21,"losses":63,"wins":160},"GB2-02":{"draws":77,"losses":9,"wins":146},"GB2-03":{"draws":67,"losses":8,"wins":159},"GB2-04":{"draws":22,"losses":11,"wins":195},"GB2-05":{"draws":0,"losses":15,"wins":211},"GB2-06":{"draws":17,"losses":25,"wins":210},"GB2-07":{"draws":0,"losses":9,"wins":275},"GB2-08":{"draws":0,"losses":21,"wins":241}},"none":{"GB2-01":{"draws":11,"losses":15,"wins":226},"GB2-02":{"draws":121,"losses":19,"wins":114},"GB2-03":{"draws":105,"losses":23,"wins":116},"GB2-04":{"draws":27,"losses":31,"wins":182},"GB2-05":{"draws":0,"losses":6,"wins":220},"GB2-06":{"draws":21,"losses":43,"wins":170},"GB2-07":{"draws":0,"losses":9,"wins":245},"GB2-08":{"draws":0,"losses":65,"wins":193}}},"per_game_raw_elo_all":{"GB2-01":2002.2218346293273,"GB2-02":1859.9028280290493,"GB2-03":1952.5413437282552,"GB2-04":1941.9566982775607,"GB2-05":2211.9821916271962,"GB2-06":1996.8073221233844,"GB2-07":2250.348341799231,"GB2-08":2030.2040582165753},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2196.543718849944,"GB2-02":2063.9275630488323,"GB2-03":2163.5190039337767,"GB2-04":1971.8262474267835,"GB2-05":2305.8243911075265,"GB2-06":2044.7653544019536,"GB2-07":2285.455463434802,"GB2-08":2052.9844485033664},"medium":{"GB2-01":1709.169890183018,"GB2-02":1807.7572388878887,"GB2-03":1963.0600032369164,"GB2-04":1961.1956366893105,"GB2-05":2081.47250029206,"GB2-06":2070.4006161095167,"GB2-07":2213.9870048414227,"GB2-08":2155.9796349618264},"none":{"GB2-01":2100.9518948550194,"GB2-02":1708.023682150427,"GB2-03":1731.0450240140724,"GB2-04":1892.848210716588,"GB2-05":2248.649683482002,"GB2-06":1875.2559958586826,"GB2-07":2251.6025571214686,"GB2-08":1881.6480911845326}},"per_game_tracks":{"highest":{"GB2-01":93.77364643873946,"GB2-02":100.0,"GB2-03":100.0,"GB2-04":97.3475278073704,"GB2-05":99.99999999999999,"GB2-06":83.44269781880206,"GB2-07":99.65604153579027,"GB2-08":80.00375714481252},"medium":{"GB2-01":58.93727047228494,"GB2-02":63.90856632210667,"GB2-03":81.14783522356228,"GB2-04":95.69162884853398,"GB2-05":85.8365396088125,"GB2-06":85.03489742391993,"GB2-07":94.95689897734873,"GB2-08":87.81008055499466},"none":{"GB2-01":87.05513481232872,"GB2-02":50.02617127882385,"GB2-03":59.39056563515839,"GB2-04":85.4755448688683,"GB2-05":96.36396331063021,"GB2-06":73.19124617557102,"GB2-07":97.38715231698653,"GB2-08":66.96573216582014}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":94.27795884318934,"medium":81.66546467894545,"none":76.98193882052338},"reasoning_agg":{"highest":{"max":100.0,"mean":94.27795884318934,"min":80.00375714481252},"medium":{"max":95.69162884853398,"mean":81.66546467894545,"min":58.93727047228494},"none":{"max":97.38715231698653,"mean":76.98193882052338,"min":50.02617127882385}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":90.95441923333112,"reasoning_variance":17.296020022665957,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.645965119111736},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":94.32329694480434,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.04533810161500185},"medium":{"ceiling_score":95.69162884853398,"expected_score":89.99547968803384,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":8.330015009088385},"none":{"ceiling_score":97.38715231698653,"expected_score":88.54448106715519,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":11.562542246631807}}},{"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":48.7391179312137},"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":9.233549636276067},"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":48.73911793121369}},"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":80.32247446404502,"highest":91.38911158312541,"medium":75.04188072111677,"none":74.53643108789285},"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":"2026-09-25T15:05:54Z","match_totals_all":{"draws":448,"losses":604,"wins":5406},"match_totals_tracks":{"highest":{"draws":70,"losses":146,"wins":2374},"medium":{"draws":161,"losses":241,"wins":1548},"none":{"draws":217,"losses":217,"wins":1484}},"model_slug":"claude-fable-5-1","overall":{"max":100.0,"mean":80.32247446404502,"min":27.6720155573788},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":2,"overall_ranking_status":"ranked","per_game":{"GB2-01":79.87031463289088,"GB2-02":93.36562317213091,"GB2-03":90.12297537243145,"GB2-04":83.69072312275135,"GB2-05":91.37112263611337,"GB2-06":100.0,"GB2-07":92.69213372868536,"GB2-08":100.0},"per_game_all":{"GB2-01":73.88361810548253,"GB2-02":79.96216199391584,"GB2-03":84.47067639181596,"GB2-04":55.39749380107537,"GB2-05":88.56746479000886,"GB2-06":86.0537814089629,"GB2-07":88.29663415792997,"GB2-08":85.9479650631687},"per_game_match_totals_all":{"GB2-01":{"draws":1,"losses":24,"wins":203},"GB2-02":{"draws":10,"losses":8,"wins":204},"GB2-03":{"draws":4,"losses":7,"wins":213},"GB2-04":{"draws":17,"losses":17,"wins":204},"GB2-05":{"draws":0,"losses":12,"wins":208},"GB2-06":{"draws":7,"losses":2,"wins":229},"GB2-07":{"draws":0,"losses":17,"wins":235},"GB2-08":{"draws":0,"losses":4,"wins":254}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":24,"wins":203},"GB2-02":{"draws":10,"losses":8,"wins":204},"GB2-03":{"draws":4,"losses":7,"wins":213},"GB2-04":{"draws":17,"losses":17,"wins":204},"GB2-05":{"draws":0,"losses":12,"wins":208},"GB2-06":{"draws":7,"losses":2,"wins":229},"GB2-07":{"draws":0,"losses":17,"wins":235},"GB2-08":{"draws":0,"losses":4,"wins":254}}},"per_game_raw_elo_all":{"GB2-01":1917.9179831839663,"GB2-02":1922.1801160610964,"GB2-03":1998.7550309663577,"GB2-04":1694.081039368708,"GB2-05":2124.589338815193,"GB2-06":2087.924601355125,"GB2-07":2115.9857123719653,"GB2-08":2131.1610509213606},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2002.0226474993385,"GB2-02":2017.5102993445785,"GB2-03":2059.1206107382654,"GB2-04":1881.2969682397602,"GB2-05":2169.720549071415,"GB2-06":2318.897092303519,"GB2-07":2181.6000531046766,"GB2-08":2316.7113153732325},"medium":{"GB2-01":1793.818548037135,"GB2-02":1958.7340226504202,"GB2-03":1972.416702123303,"GB2-04":1510.3418830394744,"GB2-05":2079.132350592878,"GB2-06":2016.1486653040506,"GB2-07":2169.7960624345815,"GB2-08":2067.7734288744737},"none":{"GB2-01":1957.9127540154252,"GB2-02":1790.2960261882906,"GB2-03":1964.727780037505,"GB2-04":1690.6042668268888,"GB2-05":2124.9151167812875,"GB2-06":1928.728046457806,"GB2-07":1996.5610215766385,"GB2-08":2008.9984085163755}},"per_game_tracks":{"highest":{"GB2-01":79.87031463289088,"GB2-02":93.36562317213091,"GB2-03":90.12297537243145,"GB2-04":83.69072312275135,"GB2-05":91.37112263611337,"GB2-06":100.0,"GB2-07":92.69213372868536,"GB2-08":100.0},"medium":{"GB2-01":65.05633016038571,"GB2-02":85.0713065691807,"GB2-03":82.02730182911166,"GB2-04":27.6720155573788,"GB2-05":85.69649309071661,"GB2-06":81.7142763946855,"GB2-07":91.91733247569104,"GB2-08":81.17998969178421},"none":{"GB2-01":76.72420952317101,"GB2-02":61.44955624043591,"GB2-03":81.26175197390472,"GB2-04":54.829742723095954,"GB2-05":88.63477864319661,"GB2-06":76.44706783220323,"GB2-07":80.28043626941351,"GB2-08":76.66390549772187}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":91.38911158312541,"medium":75.04188072111677,"none":74.53643108789285},"reasoning_agg":{"highest":{"max":100.0,"mean":91.38911158312541,"min":79.87031463289088},"medium":{"max":91.91733247569104,"mean":75.04188072111677,"min":27.6720155573788},"none":{"max":88.63477864319661,"mean":74.53643108789285,"min":54.829742723095954}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":87.24058233088488,"reasoning_variance":16.852680495232562,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.918107866839861},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":100.0,"expected_score":91.39966253282738,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.010550949701965351},"medium":{"ceiling_score":91.91733247569104,"expected_score":83.60103262158643,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":8.559151900469658},"none":{"ceiling_score":88.63477864319661,"expected_score":86.72105183824084,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":12.184620750347989}}},{"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":3.006308},"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":71.7363298403025,"highest":80.9535676866771,"medium":74.49726125112892,"none":59.7581605831015},"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":"2026-09-25T14:34:00Z","match_totals_all":{"draws":176,"losses":252,"wins":1926},"match_totals_tracks":{"highest":{"draws":22,"losses":35,"wins":663},"medium":{"draws":26,"losses":61,"wins":727},"none":{"draws":128,"losses":156,"wins":536}},"model_slug":"claude-opus-5-5","overall":{"max":90.00227559221021,"mean":71.7363298403025,"min":34.34311959065729},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":3,"overall_ranking_status":"ranked","per_game":{"GB2-01":62.15278254588686,"GB2-02":82.7940575934645,"GB2-03":77.19523136118757,"GB2-04":90.00227559221021,"GB2-05":83.89765057926846,"GB2-06":85.98139509310396,"GB2-07":88.05090981009354,"GB2-08":77.55423891820166},"per_game_all":{"GB2-01":69.06182130583721,"GB2-02":69.82768307429784,"GB2-03":60.869319711694686,"GB2-04":69.42803063610414,"GB2-05":77.54894572192887,"GB2-06":77.24770280939994,"GB2-07":83.1609279596309,"GB2-08":66.74620750352646},"per_game_match_totals_all":{"GB2-01":{"draws":10,"losses":24,"wins":206},"GB2-02":{"draws":30,"losses":14,"wins":240},"GB2-03":{"draws":48,"losses":22,"wins":122},"GB2-04":{"draws":70,"losses":22,"wins":180},"GB2-05":{"draws":0,"losses":25,"wins":221},"GB2-06":{"draws":14,"losses":22,"wins":232},"GB2-07":{"draws":0,"losses":19,"wins":285},"GB2-08":{"draws":4,"losses":104,"wins":440}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":3,"losses":17,"wins":58},"GB2-02":{"draws":5,"losses":1,"wins":90},"GB2-03":{"draws":1,"losses":0,"wins":63},"GB2-04":{"draws":12,"losses":3,"wins":77},"GB2-05":{"draws":0,"losses":2,"wins":76},"GB2-06":{"draws":1,"losses":0,"wins":91},"GB2-07":{"draws":0,"losses":1,"wins":103},"GB2-08":{"draws":0,"losses":11,"wins":105}},"medium":{"GB2-01":{"draws":4,"losses":2,"wins":74},"GB2-02":{"draws":3,"losses":4,"wins":85},"GB2-03":{"draws":3,"losses":7,"wins":54},"GB2-04":{"draws":9,"losses":10,"wins":73},"GB2-05":{"draws":0,"losses":14,"wins":72},"GB2-06":{"draws":7,"losses":7,"wins":80},"GB2-07":{"draws":0,"losses":9,"wins":89},"GB2-08":{"draws":0,"losses":8,"wins":200}},"none":{"GB2-01":{"draws":3,"losses":5,"wins":74},"GB2-02":{"draws":22,"losses":9,"wins":65},"GB2-03":{"draws":44,"losses":15,"wins":5},"GB2-04":{"draws":49,"losses":9,"wins":30},"GB2-05":{"draws":0,"losses":9,"wins":73},"GB2-06":{"draws":6,"losses":15,"wins":61},"GB2-07":{"draws":0,"losses":9,"wins":93},"GB2-08":{"draws":4,"losses":85,"wins":135}}},"per_game_raw_elo_all":{"GB2-01":1869.283756131378,"GB2-02":1864.4854115084556,"GB2-03":1770.8364101118314,"GB2-04":1802.5534713078086,"GB2-05":1967.2464831639156,"GB2-06":1958.4647530765105,"GB2-07":2053.8417804255782,"GB2-08":1891.7988240532834},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1773.4684559371246,"GB2-02":1956.270414304034,"GB2-03":1944.5287804487727,"GB2-04":1938.5493344877893,"GB2-05":2069.1372139350938,"GB2-06":2102.4016317134924,"GB2-07":2126.288409526174,"GB2-08":2033.2245619528665},"medium":{"GB2-01":1914.6552626349105,"GB2-02":1907.3870916629003,"GB2-03":1879.3579016389629,"GB2-04":1805.3403032296576,"GB2-05":1853.5470877597693,"GB2-06":1959.1974935170713,"GB2-07":2030.8784144609388,"GB2-08":2034.8111199288733},"none":{"GB2-01":1919.7275498220986,"GB2-02":1729.7987285584331,"GB2-03":1488.622548247758,"GB2-04":1663.7707762059795,"GB2-05":1979.0551477968836,"GB2-06":1813.795133998968,"GB2-07":2004.3585172896226,"GB2-08":1607.3607902781105}},"per_game_tracks":{"highest":{"GB2-01":62.15278254588686,"GB2-02":82.7940575934645,"GB2-03":77.19523136118757,"GB2-04":90.00227559221021,"GB2-05":83.89765057926846,"GB2-06":85.98139509310396,"GB2-07":88.05090981009354,"GB2-08":77.55423891820166},"medium":{"GB2-01":72.31520041908865,"GB2-02":75.78826057875526,"GB2-03":71.06960818323918,"GB2-04":69.8950709756612,"GB2-05":70.45502164921955,"GB2-06":77.35850943307017,"GB2-07":81.57822709514194,"GB2-08":77.51819167485543},"none":{"GB2-01":72.71748095253615,"GB2-02":50.90073105067378,"GB2-03":34.34311959065729,"GB2-04":48.386745340440996,"GB2-05":78.29416493729859,"GB2-06":68.40320390202572,"GB2-07":79.85364697365718,"GB2-08":45.166191917522255}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":80.9535676866771,"medium":74.49726125112892,"none":59.7581605831015},"reasoning_agg":{"highest":{"max":90.00227559221021,"mean":80.9535676866771,"min":62.15278254588686},"medium":{"max":81.57822709514194,"mean":74.49726125112892,"min":69.8950709756612},"none":{"max":79.85364697365718,"mean":59.7581605831015,"min":34.34311959065729}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":90.00227559221021,"expected_score":77.99728189198163,"reasoning_variance":21.195407103575604,"reliability_score":90.58257813228255,"uncertainty_avg":9.417421867717447,"uncertainty_penalty":6.260952051679126},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":90.00227559221021,"expected_score":80.48381849989474,"reliability_score":90.7489181104426,"uncertainty_avg":9.2510818895574,"uncertainty_penalty":-0.46974918678236577},"medium":{"ceiling_score":81.57822709514194,"expected_score":83.55695487868162,"reliability_score":90.5967285484301,"uncertainty_avg":9.403271451569907,"uncertainty_penalty":9.059693627552704},"none":{"ceiling_score":79.85364697365718,"expected_score":69.9510722973685,"reliability_score":90.40208773797497,"uncertainty_avg":9.597912262025032,"uncertainty_penalty":10.192911714266998}}},{"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":22.074450000000002},"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":7.1388750000000005},"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":4.570125000000001}},"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":4.570125000000001},"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":64.75152406396425,"highest":76.79197650973506,"medium":61.757649808905576,"none":59.77980290368503},"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":"2026-09-25T15:14:25Z","match_totals_all":{"draws":1172,"losses":1355,"wins":5874},"match_totals_tracks":{"highest":{"draws":155,"losses":326,"wins":1885},"medium":{"draws":387,"losses":485,"wins":2042},"none":{"draws":630,"losses":544,"wins":1947}},"model_slug":"claude-opus-5","overall":{"max":90.34746663281791,"mean":63.4848578652761,"min":15.978871709726342},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":4,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.671054671727674,"GB2-02":65.01945157758348,"GB2-03":89.1770885247866,"GB2-04":74.54068913938104,"GB2-05":90.34746663281791,"GB2-07":88.9097764968694,"GB2-08":69.8783085249793},"per_game_all":{"GB2-01":60.106929478794996,"GB2-02":51.42813534488622,"GB2-03":65.0647631441342,"GB2-04":40.46621492534746,"GB2-05":86.85648461636283,"GB2-07":81.95915900065374,"GB2-08":67.37898193757034},"per_game_match_totals_all":{"GB2-01":{"draws":215,"losses":229,"wins":635},"GB2-02":{"draws":430,"losses":93,"wins":688},"GB2-03":{"draws":61,"losses":164,"wins":628},"GB2-04":{"draws":404,"losses":330,"wins":560},"GB2-05":{"draws":0,"losses":106,"wins":1054},"GB2-06":{"draws":9,"losses":10,"wins":199},"GB2-07":{"draws":0,"losses":116,"wins":800},"GB2-08":{"draws":53,"losses":307,"wins":1310}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":4,"losses":103,"wins":213},"GB2-02":{"draws":88,"losses":35,"wins":245},"GB2-03":{"draws":5,"losses":13,"wins":240},"GB2-04":{"draws":58,"losses":50,"wins":292},"GB2-05":{"draws":0,"losses":28,"wins":316},"GB2-07":{"draws":0,"losses":9,"wins":199},"GB2-08":{"draws":0,"losses":88,"wins":380}},"medium":{"GB2-01":{"draws":41,"losses":93,"wins":236},"GB2-02":{"draws":154,"losses":26,"wins":215},"GB2-03":{"draws":5,"losses":40,"wins":252},"GB2-04":{"draws":187,"losses":153,"wins":116},"GB2-05":{"draws":0,"losses":47,"wins":363},"GB2-07":{"draws":0,"losses":67,"wins":405},"GB2-08":{"draws":0,"losses":59,"wins":455}},"none":{"GB2-01":{"draws":170,"losses":33,"wins":186},"GB2-02":{"draws":188,"losses":32,"wins":228},"GB2-03":{"draws":51,"losses":111,"wins":136},"GB2-04":{"draws":159,"losses":127,"wins":152},"GB2-05":{"draws":0,"losses":31,"wins":375},"GB2-06":{"draws":9,"losses":10,"wins":199},"GB2-07":{"draws":0,"losses":40,"wins":196},"GB2-08":{"draws":53,"losses":160,"wins":475}}},"per_game_raw_elo_all":{"GB2-01":1729.789621733159,"GB2-02":1721.0860450894816,"GB2-03":1799.3712291479144,"GB2-04":1596.1054240158276,"GB2-05":2099.891354339745,"GB2-07":2022.9110977811772,"GB2-08":1886.536562310689},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1725.375924521653,"GB2-02":1818.8505392710506,"GB2-03":2057.4923993127013,"GB2-04":1822.8530033140737,"GB2-05":2156.975351125996,"GB2-07":2127.7356846387693,"GB2-08":1921.245931887621},"medium":{"GB2-01":1705.0749290256176,"GB2-02":1673.9642494443597,"GB2-03":1878.832615588344,"GB2-04":1433.1064001968423,"GB2-05":2024.0282553062893,"GB2-07":2015.2147642946993,"GB2-08":2013.6159955111561},"none":{"GB2-01":1758.9180116522066,"GB2-02":1670.4433465530342,"GB2-03":1461.788672542698,"GB2-04":1532.3568685365676,"GB2-05":2118.6704565869495,"GB2-06":2126.4040981564867,"GB2-07":1925.7828444100635,"GB2-08":1724.7477595332903}},"per_game_tracks":{"highest":{"GB2-01":59.671054671727674,"GB2-02":65.01945157758348,"GB2-03":89.1770885247866,"GB2-04":74.54068913938104,"GB2-05":90.34746663281791,"GB2-07":88.9097764968694,"GB2-08":69.8783085249793},"medium":{"GB2-01":58.364791089349026,"GB2-02":44.759035246055106,"GB2-03":72.60400026322671,"GB2-04":15.978871709726342,"GB2-05":82.13477554310234,"GB2-07":81.48022089997005,"GB2-08":76.98185391090948},"none":{"GB2-01":62.28494267530827,"GB2-02":44.505919211020085,"GB2-03":33.4132006443893,"GB2-04":30.879083926934985,"GB2-05":88.08721167316827,"GB2-06":88.30380211671529,"GB2-07":75.48747960512179,"GB2-08":55.276783376822266}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":72.90741299156647,"medium":59.73003562775136,"none":57.81712497651046},"reasoning_agg":{"highest":{"max":90.34746663281791,"mean":72.90741299156647,"min":59.671054671727674},"medium":{"max":82.13477554310234,"mean":59.73003562775136,"min":15.978871709726342},"none":{"max":88.30380211671529,"mean":57.81712497651046,"min":30.879083926934985}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":90.34746663281791,"expected_score":68.96856294253948,"reasoning_variance":15.09028801505601,"reliability_score":99.97687239166677,"uncertainty_avg":0.02312760833323324,"uncertainty_penalty":5.48370507726338},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":90.34746663281791,"expected_score":75.01480022964721,"reliability_score":99.9306171750003,"uncertainty_avg":0.06938282499969972,"uncertainty_penalty":2.107387238080733},"medium":{"ceiling_score":82.13477554310234,"expected_score":68.43488800878134,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":8.70485238102998},"none":{"ceiling_score":88.30380211671529,"expected_score":68.02400051554118,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":10.206875539030712}}},{"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":3.104419565},"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":0.43181688}},"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":1.25555516},"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":60.07551994914719,"highest":79.76036427478273,"medium":60.37629544290532,"none":38.754746612238606},"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":"2026-09-25T16:20:12Z","match_totals_all":{"draws":1311,"losses":1419,"wins":3321},"match_totals_tracks":{"highest":{"draws":193,"losses":155,"wins":1378},"medium":{"draws":377,"losses":497,"wins":1224},"none":{"draws":741,"losses":767,"wins":719}},"model_slug":"z-ai-glm-5-3","overall":{"max":97.58127501121015,"mean":59.630468776642225,"min":15.003603712634062},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":5,"overall_ranking_status":"partial","per_game":{"GB2-01":75.80228272363448,"GB2-02":39.53484749867363,"GB2-03":84.96955467101989,"GB2-05":92.95824569345824,"GB2-06":90.7636514969772,"GB2-07":97.58127501121015,"GB2-08":76.7126928285054},"per_game_all":{"GB2-01":60.04284226097516,"GB2-02":26.02865364742736,"GB2-03":59.50297621121223,"GB2-05":71.4483579349017,"GB2-06":77.79055361202994,"GB2-07":77.54002786137787,"GB2-08":48.17522811610602},"per_game_match_totals_all":{"GB2-01":{"draws":111,"losses":229,"wins":460},"GB2-02":{"draws":545,"losses":93,"wins":130},"GB2-03":{"draws":164,"losses":189,"wins":413},"GB2-04":{"draws":207,"losses":64,"wins":224},"GB2-05":{"draws":0,"losses":241,"wins":519},"GB2-06":{"draws":44,"losses":187,"wins":601},"GB2-07":{"draws":0,"losses":186,"wins":596},"GB2-08":{"draws":240,"losses":230,"wins":378}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":19,"losses":23,"wins":190},"GB2-02":{"draws":133,"losses":18,"wins":87},"GB2-03":{"draws":23,"losses":32,"wins":199},"GB2-05":{"draws":0,"losses":16,"wins":218},"GB2-06":{"draws":18,"losses":13,"wins":219},"GB2-07":{"draws":0,"losses":11,"wins":247},"GB2-08":{"draws":0,"losses":42,"wins":218}},"medium":{"GB2-01":{"draws":50,"losses":123,"wins":141},"GB2-02":{"draws":163,"losses":33,"wins":36},"GB2-03":{"draws":29,"losses":48,"wins":146},"GB2-04":{"draws":36,"losses":21,"wins":188},"GB2-05":{"draws":0,"losses":98,"wins":142},"GB2-06":{"draws":14,"losses":12,"wins":230},"GB2-07":{"draws":0,"losses":79,"wins":183},"GB2-08":{"draws":85,"losses":83,"wins":158}},"none":{"GB2-01":{"draws":42,"losses":83,"wins":129},"GB2-02":{"draws":249,"losses":42,"wins":7},"GB2-03":{"draws":112,"losses":109,"wins":68},"GB2-04":{"draws":171,"losses":43,"wins":36},"GB2-05":{"draws":0,"losses":127,"wins":159},"GB2-06":{"draws":12,"losses":162,"wins":152},"GB2-07":{"draws":0,"losses":96,"wins":166},"GB2-08":{"draws":155,"losses":105,"wins":2}}},"per_game_raw_elo_all":{"GB2-01":1723.6324910090627,"GB2-02":1537.6409034204144,"GB2-03":1731.7738725977094,"GB2-05":1851.5938069737092,"GB2-06":1949.4178992039535,"GB2-07":1955.153349869949,"GB2-08":1633.1694337602664},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1945.0536760331718,"GB2-02":1634.350599063675,"GB2-03":2002.6753583822758,"GB2-05":2194.1105298945445,"GB2-06":2165.3489889633206,"GB2-07":2254.304779047959,"GB2-08":2009.920716462801},"medium":{"GB2-01":1593.6235685063568,"GB2-02":1521.1569523858368,"GB2-03":1735.032721767681,"GB2-04":1783.7259066666843,"GB2-05":1814.0769167802891,"GB2-06":2174.6692101629533,"GB2-07":1799.0069770627845,"GB2-08":1687.3866173471636},"none":{"GB2-01":1632.22022848766,"GB2-02":1457.4151588117313,"GB2-03":1457.613537643171,"GB2-04":1463.468110312634,"GB2-05":1546.5939742462938,"GB2-06":1508.2354984855863,"GB2-07":1812.148293499103,"GB2-08":1202.2009674708343}},"per_game_tracks":{"highest":{"GB2-01":75.80228272363448,"GB2-02":39.53484749867363,"GB2-03":84.96955467101989,"GB2-05":92.95824569345824,"GB2-06":90.7636514969772,"GB2-07":97.58127501121015,"GB2-08":76.7126928285054},"medium":{"GB2-01":50.86956687787791,"GB2-02":23.547509730974397,"GB2-03":59.655310442580365,"GB2-04":69.04383353117605,"GB2-05":69.04748335935413,"GB2-06":91.34449020371359,"GB2-07":67.07902568340647,"GB2-08":52.42314371415959},"none":{"GB2-01":53.45667718141312,"GB2-02":15.003603712634062,"GB2-03":33.884063520036406,"GB2-04":20.741133901363547,"GB2-05":52.33934475189269,"GB2-06":51.263519135398994,"GB2-07":67.95978288951696,"GB2-08":15.38984780565305}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":79.76036427478273,"medium":60.37629544290532,"none":38.754746612238606},"reasoning_agg":{"highest":{"max":97.58127501121015,"mean":79.76036427478273,"min":39.53484749867363},"medium":{"max":91.34449020371359,"mean":60.37629544290532,"min":23.547509730974397},"none":{"max":67.95978288951696,"mean":38.754746612238606,"min":15.003603712634062}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":97.58127501121015,"expected_score":61.694977058107604,"reasoning_variance":41.005617662544125,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.064508281465379},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":97.58127501121015,"expected_score":77.60365870014004,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.156705574642686},"medium":{"ceiling_score":91.34449020371359,"expected_score":64.94769509817775,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.57139965527243},"none":{"ceiling_score":67.95978288951696,"expected_score":40.54091213037253,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7861655181339273}}},{"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":1.8325050000000003},"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":6.37255375}},"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":9.227983749999998},"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":56.25083621933662,"highest":69.89581987459516,"medium":56.590178181129204,"none":42.26651060228551},"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":"2026-09-25T16:02:44Z","match_totals_all":{"draws":1327,"losses":2172,"wins":4849},"match_totals_tracks":{"highest":{"draws":195,"losses":438,"wins":1984},"medium":{"draws":422,"losses":729,"wins":1485},"none":{"draws":710,"losses":1005,"wins":1380}},"model_slug":"gpt-5-6-sol","overall":{"max":89.24673663502878,"mean":56.25083621933663,"min":9.182072363962202},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":6,"overall_ranking_status":"ranked","per_game":{"GB2-01":64.97146846724627,"GB2-02":51.53506842461099,"GB2-03":61.971421270163184,"GB2-04":75.61817300254005,"GB2-05":71.44710951598115,"GB2-06":80.83425675693161,"GB2-07":89.24673663502878,"GB2-08":63.542324924259354},"per_game_all":{"GB2-01":61.64513602897392,"GB2-02":33.953481231910516,"GB2-03":50.84838506264712,"GB2-04":52.013166051289716,"GB2-05":65.74362152781798,"GB2-06":61.65834172160504,"GB2-07":64.7198658555114,"GB2-08":59.42469227493731},"per_game_match_totals_all":{"GB2-01":{"draws":81,"losses":291,"wins":586},"GB2-02":{"draws":542,"losses":108,"wins":332},"GB2-03":{"draws":199,"losses":282,"wins":540},"GB2-04":{"draws":361,"losses":153,"wins":477},"GB2-05":{"draws":0,"losses":334,"wins":716},"GB2-06":{"draws":46,"losses":390,"wins":673},"GB2-07":{"draws":0,"losses":353,"wins":796},"GB2-08":{"draws":98,"losses":261,"wins":729}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":101,"wins":207},"GB2-02":{"draws":108,"losses":27,"wins":197},"GB2-03":{"draws":7,"losses":57,"wins":245},"GB2-04":{"draws":43,"losses":25,"wins":234},"GB2-05":{"draws":0,"losses":85,"wins":249},"GB2-06":{"draws":29,"losses":33,"wins":266},"GB2-07":{"draws":0,"losses":30,"wins":312},"GB2-08":{"draws":0,"losses":80,"wins":274}},"medium":{"GB2-01":{"draws":71,"losses":101,"wins":144},"GB2-02":{"draws":162,"losses":29,"wins":111},"GB2-03":{"draws":38,"losses":104,"wins":175},"GB2-04":{"draws":77,"losses":26,"wins":208},"GB2-05":{"draws":0,"losses":73,"wins":239},"GB2-06":{"draws":6,"losses":184,"wins":158},"GB2-07":{"draws":0,"losses":99,"wins":271},"GB2-08":{"draws":68,"losses":113,"wins":179}},"none":{"GB2-01":{"draws":2,"losses":89,"wins":235},"GB2-02":{"draws":272,"losses":52,"wins":24},"GB2-03":{"draws":154,"losses":121,"wins":120},"GB2-04":{"draws":241,"losses":102,"wins":35},"GB2-05":{"draws":0,"losses":176,"wins":228},"GB2-06":{"draws":11,"losses":173,"wins":249},"GB2-07":{"draws":0,"losses":224,"wins":213},"GB2-08":{"draws":30,"losses":68,"wins":276}}},"per_game_raw_elo_all":{"GB2-01":1743.735104964054,"GB2-02":1590.9475538889674,"GB2-03":1636.3592196246454,"GB2-04":1667.4528686264948,"GB2-05":1757.2914043343033,"GB2-06":1679.1060870780539,"GB2-07":1759.6346918382562,"GB2-08":1778.4568137649403},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1790.2463407968028,"GB2-02":1715.609120411484,"GB2-03":1755.6663153829472,"GB2-04":1824.75684458976,"GB2-05":1848.2714359945248,"GB2-06":1997.7574443097017,"GB2-07":2126.6926815025818,"GB2-08":1832.936624227382},"medium":{"GB2-01":1645.9125422305578,"GB2-02":1608.969068467395,"GB2-03":1670.9434445351742,"GB2-04":1795.4129004500003,"GB2-05":1904.2282775886874,"GB2-06":1435.6403620647127,"GB2-07":1800.2013496000136,"GB2-08":1617.402338037299},"none":{"GB2-01":1795.0464318648021,"GB2-02":1448.2644727880233,"GB2-03":1482.4678989558154,"GB2-04":1382.1888608397242,"GB2-05":1519.3744994196975,"GB2-06":1603.9204548597472,"GB2-07":1352.0100444121738,"GB2-08":1885.03147903014}},"per_game_tracks":{"highest":{"GB2-01":64.97146846724627,"GB2-02":51.53506842461099,"GB2-03":61.971421270163184,"GB2-04":75.61817300254005,"GB2-05":71.44710951598115,"GB2-06":80.83425675693161,"GB2-07":89.24673663502878,"GB2-08":63.542324924259354},"medium":{"GB2-01":54.62351061515375,"GB2-02":36.36805948391099,"GB2-03":54.03507393286738,"GB2-04":71.23925278736691,"GB2-05":74.92326063693565,"GB2-06":46.921635612672766,"GB2-07":67.42033275926899,"GB2-08":47.19029962085715},"none":{"GB2-01":65.34042900452175,"GB2-02":13.95731578720957,"GB2-03":36.5386599849108,"GB2-04":9.182072363962202,"GB2-05":50.86049443053713,"GB2-06":57.21913279521076,"GB2-07":37.492528172236426,"GB2-08":67.54145227969542}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":69.89581987459516,"medium":56.590178181129204,"none":42.26651060228551},"reasoning_agg":{"highest":{"max":89.24673663502878,"mean":69.89581987459516,"min":51.53506842461099},"medium":{"max":74.92326063693565,"mean":56.590178181129204,"min":36.36805948391099},"none":{"max":67.54145227969542,"mean":42.26651060228551,"min":9.182072363962202}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":89.24673663502878,"expected_score":56.7400867112134,"reasoning_variance":27.629309272309655,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.48925049187677416},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":89.24673663502878,"expected_score":65.64696245675748,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.248857417837684},"medium":{"ceiling_score":74.92326063693565,"expected_score":59.14289037535699,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.5527121942277873},"none":{"ceiling_score":67.54145227969542,"expected_score":45.430407301525726,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.163896699240219}}},{"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":1.5822288},"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":0.663736}},"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":1.889224},"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":4.135188800000001},"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":56.867308306090884,"highest":61.511708255394375,"medium":67.44242954428366,"none":39.01861015130885},"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":"2026-09-25T13:22:25Z","match_totals_all":{"draws":149,"losses":388,"wins":867},"match_totals_tracks":{"highest":{"draws":13,"losses":58,"wins":211},"medium":{"draws":18,"losses":87,"wins":417},"none":{"draws":118,"losses":243,"wins":239}},"model_slug":"x-ai-grok-4-7","overall":{"max":81.37689077370601,"mean":55.56389904720976,"min":15.846953534414173},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":7,"overall_ranking_status":"partial","per_game":{"GB2-01":58.418768085533685,"GB2-07":60.720023895279155,"GB2-08":65.39633278537028},"per_game_all":{"GB2-01":50.073755592978934,"GB2-07":56.9583244373194,"GB2-08":63.56984488797432},"per_game_match_totals_all":{"GB2-01":{"draws":39,"losses":79,"wins":122},"GB2-02":{"draws":62,"losses":16,"wins":10},"GB2-03":{"draws":6,"losses":11,"wins":43},"GB2-04":{"draws":29,"losses":50,"wins":87},"GB2-05":{"draws":0,"losses":54,"wins":100},"GB2-06":{"draws":11,"losses":15,"wins":58},"GB2-07":{"draws":0,"losses":115,"wins":199},"GB2-08":{"draws":2,"losses":48,"wins":248}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":11,"losses":19,"wins":52},"GB2-07":{"draws":0,"losses":29,"wins":71},"GB2-08":{"draws":2,"losses":10,"wins":88}},"medium":{"GB2-01":{"draws":1,"losses":19,"wins":62},"GB2-03":{"draws":6,"losses":11,"wins":43},"GB2-04":{"draws":11,"losses":8,"wins":67},"GB2-05":{"draws":0,"losses":4,"wins":78},"GB2-07":{"draws":0,"losses":34,"wins":78},"GB2-08":{"draws":0,"losses":11,"wins":89}},"none":{"GB2-01":{"draws":27,"losses":41,"wins":8},"GB2-02":{"draws":62,"losses":16,"wins":10},"GB2-04":{"draws":18,"losses":42,"wins":20},"GB2-05":{"draws":0,"losses":50,"wins":22},"GB2-06":{"draws":11,"losses":15,"wins":58},"GB2-07":{"draws":0,"losses":52,"wins":50},"GB2-08":{"draws":0,"losses":27,"wins":71}}},"per_game_raw_elo_all":{"GB2-01":1604.451321667835,"GB2-07":1662.284075203833,"GB2-08":1852.004097324705},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1720.288436114733,"GB2-07":1719.264076773523,"GB2-08":1875.9257072480004},"medium":{"GB2-01":1770.0444447829527,"GB2-03":1737.3085217737114,"GB2-04":1791.0168893205353,"GB2-05":2028.0093303656413,"GB2-07":1767.6454148188684,"GB2-08":1964.1506967203081},"none":{"GB2-01":1323.0210841058188,"GB2-02":1487.5547550320823,"GB2-04":1450.2411256233731,"GB2-05":1380.565203529387,"GB2-06":1860.3173121974187,"GB2-07":1499.942734019108,"GB2-08":1715.9358880058066}},"per_game_tracks":{"highest":{"GB2-01":58.418768085533685,"GB2-07":60.720023895279155,"GB2-08":65.39633278537028},"medium":{"GB2-01":61.986006568145754,"GB2-03":57.56745440692937,"GB2-04":67.52073299307726,"GB2-05":81.37689077370601,"GB2-07":64.10825307420451,"GB2-08":72.09523944963898},"none":{"GB2-01":29.816492125257373,"GB2-02":16.534713974406596,"GB2-04":15.846953534414173,"GB2-05":40.42296831994141,"GB2-06":71.24448433375413,"GB2-07":46.04669634247453,"GB2-08":53.21796242891374}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":61.511708255394375,"medium":67.44242954428366,"none":37.73755934195125},"reasoning_agg":{"highest":{"max":65.39633278537028,"mean":61.511708255394375,"min":58.418768085533685},"medium":{"max":81.37689077370601,"mean":67.44242954428366,"min":57.56745440692937},"none":{"max":71.24448433375413,"mean":37.73755934195125,"min":15.846953534414173}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":81.37689077370601,"expected_score":58.56608256197493,"reasoning_variance":29.70487020233241,"reliability_score":92.35505279540413,"uncertainty_avg":7.644947204595868,"uncertainty_penalty":3.0021835147651714},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":65.39633278537028,"expected_score":58.66914066522051,"reliability_score":92.28805032805197,"uncertainty_avg":7.711949671948031,"uncertainty_penalty":-2.8425675901738643},"medium":{"ceiling_score":81.37689077370601,"expected_score":75.13309925767408,"reliability_score":89.7206283953821,"uncertainty_avg":10.279371604617898,"uncertainty_penalty":7.69066971339042},"none":{"ceiling_score":71.24448433375413,"expected_score":43.3719931295728,"reliability_score":89.77753135577184,"uncertainty_avg":10.22246864422816,"uncertainty_penalty":5.634433787621553}}},{"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":0.6265165},"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":0.6265165},"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":2.626442500000001},"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":55.13066598615362,"highest":61.55693513846125,"medium":57.34076897878964,"none":46.49429384120996},"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":"2026-09-25T14:29:47Z","match_totals_all":{"draws":321,"losses":479,"wins":1332},"match_totals_tracks":{"highest":{"draws":64,"losses":121,"wins":507},"medium":{"draws":124,"losses":144,"wins":452},"none":{"draws":133,"losses":214,"wins":373}},"model_slug":"gpt-6-sol","overall":{"max":82.55615873333252,"mean":55.130665986153616,"min":11.206070516617746},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":8,"overall_ranking_status":"ranked","per_game":{"GB2-01":11.206070516617746,"GB2-02":39.644601832444756,"GB2-03":72.72412581235643,"GB2-04":62.103159443224804,"GB2-05":75.30573119224167,"GB2-06":81.84045926750574,"GB2-07":82.55615873333252,"GB2-08":67.07517430996639},"per_game_all":{"GB2-01":29.473154997507326,"GB2-02":29.122583120111596,"GB2-03":58.66955100444884,"GB2-04":42.10998555304517,"GB2-05":73.01351880021618,"GB2-06":71.56878179639695,"GB2-07":73.13374424110144,"GB2-08":63.954008376401475},"per_game_match_totals_all":{"GB2-01":{"draws":23,"losses":145,"wins":54},"GB2-02":{"draws":151,"losses":46,"wins":99},"GB2-03":{"draws":10,"losses":36,"wins":134},"GB2-04":{"draws":92,"losses":53,"wins":115},"GB2-05":{"draws":0,"losses":34,"wins":222},"GB2-06":{"draws":41,"losses":48,"wins":193},"GB2-07":{"draws":0,"losses":58,"wins":254},"GB2-08":{"draws":4,"losses":59,"wins":261}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":64,"wins":4},"GB2-02":{"draws":37,"losses":5,"wins":50},"GB2-03":{"draws":0,"losses":4,"wins":54},"GB2-04":{"draws":15,"losses":10,"wins":59},"GB2-05":{"draws":0,"losses":5,"wins":77},"GB2-06":{"draws":9,"losses":8,"wins":73},"GB2-07":{"draws":0,"losses":9,"wins":99},"GB2-08":{"draws":1,"losses":16,"wins":91}},"medium":{"GB2-01":{"draws":16,"losses":43,"wins":15},"GB2-02":{"draws":50,"losses":16,"wins":38},"GB2-03":{"draws":4,"losses":19,"wins":35},"GB2-04":{"draws":30,"losses":13,"wins":47},"GB2-05":{"draws":0,"losses":8,"wins":80},"GB2-06":{"draws":22,"losses":17,"wins":63},"GB2-07":{"draws":0,"losses":8,"wins":90},"GB2-08":{"draws":2,"losses":20,"wins":84}},"none":{"GB2-01":{"draws":5,"losses":38,"wins":35},"GB2-02":{"draws":64,"losses":25,"wins":11},"GB2-03":{"draws":6,"losses":13,"wins":45},"GB2-04":{"draws":47,"losses":30,"wins":9},"GB2-05":{"draws":0,"losses":21,"wins":65},"GB2-06":{"draws":10,"losses":23,"wins":57},"GB2-07":{"draws":0,"losses":41,"wins":65},"GB2-08":{"draws":1,"losses":23,"wins":86}}},"per_game_raw_elo_all":{"GB2-01":1318.8689058902726,"GB2-02":1574.6453693425685,"GB2-03":1749.0740502977449,"GB2-04":1622.521697277017,"GB2-05":1894.3553065452381,"GB2-06":1863.3924525659934,"GB2-07":1903.7425423493053,"GB2-08":1855.4450004162354},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1065.329091592359,"GB2-02":1650.7341735576565,"GB2-03":1899.422086219661,"GB2-04":1755.6273778628556,"GB2-05":1931.5983388188122,"GB2-06":2034.2953622376588,"GB2-07":2043.581158442173,"GB2-08":1896.5477113421146},"medium":{"GB2-01":1365.892434022501,"GB2-02":1591.9785633907034,"GB2-03":1686.2818549800577,"GB2-04":1688.9460438675994,"GB2-05":1952.0875485730328,"GB2-06":1829.9362462808288,"GB2-07":1990.2209917943844,"GB2-08":1856.7161709916622},"none":{"GB2-01":1525.3851920559573,"GB2-02":1481.2233710793464,"GB2-03":1661.5182096935155,"GB2-04":1422.9916701005964,"GB2-05":1799.3800322438697,"GB2-06":1725.945749179493,"GB2-07":1677.4254768113583,"GB2-08":1813.07111891493}},"per_game_tracks":{"highest":{"GB2-01":11.206070516617746,"GB2-02":39.644601832444756,"GB2-03":72.72412581235643,"GB2-04":62.103159443224804,"GB2-05":75.30573119224167,"GB2-06":81.84045926750574,"GB2-07":82.55615873333252,"GB2-08":67.07517430996639},"medium":{"GB2-01":32.84684899959481,"GB2-02":31.714134573439228,"GB2-03":52.69038122461175,"GB2-04":52.257540853318176,"GB2-05":76.69079262608564,"GB2-06":69.64945689149215,"GB2-07":78.85328563520711,"GB2-08":64.02371102656826},"none":{"GB2-01":44.366545476309426,"GB2-02":16.009012954450796,"GB2-03":50.59414597637835,"GB2-04":11.969256362592526,"GB2-05":67.0440325823212,"GB2-06":63.21642923019296,"GB2-07":57.99178835476464,"GB2-08":60.76313979266979}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":61.55693513846125,"medium":57.34076897878964,"none":46.49429384120996},"reasoning_agg":{"highest":{"max":82.55615873333252,"mean":61.55693513846125,"min":11.206070516617746},"medium":{"max":78.85328563520711,"mean":57.34076897878964,"min":31.714134573439228},"none":{"max":67.0440325823212,"mean":46.49429384120996,"min":11.969256362592526}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":82.55615873333252,"expected_score":57.90423261747106,"reasoning_variance":15.06264129725129,"reliability_score":90.336234151158,"uncertainty_avg":9.663765848842003,"uncertainty_penalty":2.7735666313174434},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":82.55615873333252,"expected_score":58.17541133815331,"reliability_score":89.55090775695673,"uncertainty_avg":10.449092243043268,"uncertainty_penalty":-3.3815238003079386},"medium":{"ceiling_score":78.85328563520711,"expected_score":63.00850228427999,"reliability_score":90.63827487291582,"uncertainty_avg":9.361725127084192,"uncertainty_penalty":5.667733305490351},"none":{"ceiling_score":67.0440325823212,"expected_score":52.52878422997987,"reliability_score":90.81951982360144,"uncertainty_avg":9.180480176398554,"uncertainty_penalty":6.03449038876991}}},{"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":11.764549999999998},"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":11.76455}},"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":18.260500000000004},"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":54.994605645666795,"highest":65.1419679067195,"medium":53.2483566362053,"none":46.59349239407559},"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":"2026-09-25T14:59:44Z","match_totals_all":{"draws":1219,"losses":1627,"wins":3191},"match_totals_tracks":{"highest":{"draws":309,"losses":454,"wins":1220},"medium":{"draws":383,"losses":546,"wins":1037},"none":{"draws":527,"losses":627,"wins":934}},"model_slug":"claude-fable-5","overall":{"max":85.53702993381843,"mean":54.9946056456668,"min":8.30135369548809},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":9,"overall_ranking_status":"ranked","per_game":{"GB2-01":73.84725078211831,"GB2-02":59.21782579520304,"GB2-03":68.91099828064931,"GB2-04":85.53702993381843,"GB2-05":52.95569071867738,"GB2-06":84.1691849172907,"GB2-07":61.26424951289066,"GB2-08":35.23351331310822},"per_game_all":{"GB2-01":63.80951204125906,"GB2-02":34.534182720004246,"GB2-03":36.24860472371338,"GB2-04":41.053314050566975,"GB2-05":61.92487838195692,"GB2-06":76.59832343674155,"GB2-07":62.502832291882186,"GB2-08":63.28519751921008},"per_game_match_totals_all":{"GB2-01":{"draws":62,"losses":193,"wins":437},"GB2-02":{"draws":391,"losses":81,"wins":216},"GB2-03":{"draws":249,"losses":249,"wins":204},"GB2-04":{"draws":343,"losses":172,"wins":264},"GB2-05":{"draws":0,"losses":325,"wins":467},"GB2-06":{"draws":55,"losses":129,"wins":528},"GB2-07":{"draws":0,"losses":328,"wins":532},"GB2-08":{"draws":119,"losses":150,"wins":543}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":36,"wins":186},"GB2-02":{"draws":77,"losses":20,"wins":133},"GB2-03":{"draws":73,"losses":23,"wins":144},"GB2-04":{"draws":27,"losses":29,"wins":179},"GB2-05":{"draws":0,"losses":137,"wins":153},"GB2-06":{"draws":14,"losses":31,"wins":193},"GB2-07":{"draws":0,"losses":101,"wins":161},"GB2-08":{"draws":118,"losses":77,"wins":71}},"medium":{"GB2-01":{"draws":25,"losses":78,"wins":127},"GB2-02":{"draws":140,"losses":28,"wins":66},"GB2-03":{"draws":64,"losses":142,"wins":20},"GB2-04":{"draws":127,"losses":54,"wins":59},"GB2-05":{"draws":0,"losses":94,"wins":156},"GB2-06":{"draws":27,"losses":41,"wins":174},"GB2-07":{"draws":0,"losses":87,"wins":171},"GB2-08":{"draws":0,"losses":22,"wins":264}},"none":{"GB2-01":{"draws":37,"losses":79,"wins":124},"GB2-02":{"draws":174,"losses":33,"wins":17},"GB2-03":{"draws":112,"losses":84,"wins":40},"GB2-04":{"draws":189,"losses":89,"wins":26},"GB2-05":{"draws":0,"losses":94,"wins":158},"GB2-06":{"draws":14,"losses":57,"wins":161},"GB2-07":{"draws":0,"losses":140,"wins":200},"GB2-08":{"draws":1,"losses":51,"wins":208}}},"per_game_raw_elo_all":{"GB2-01":1777.863184829261,"GB2-02":1599.3267582756955,"GB2-03":1485.3805568987982,"GB2-04":1597.689976332845,"GB2-05":1699.817196662575,"GB2-06":1931.4852156732507,"GB2-07":1729.789958987002,"GB2-08":1832.6038571264107},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1918.3659092889625,"GB2-02":1774.561902563198,"GB2-03":1832.5446903752695,"GB2-04":1893.5270627446387,"GB2-05":1556.2188092504707,"GB2-06":2056.7934715850724,"GB2-07":1712.247750873124,"GB2-08":1463.357739447561},"medium":{"GB2-01":1676.2121600864764,"GB2-02":1610.0612275564356,"GB2-03":1248.3349928557948,"GB2-04":1507.571534971346,"GB2-05":1776.9643555457678,"GB2-06":1903.2394730829708,"GB2-07":1792.3257562370536,"GB2-08":2103.0202723204475},"none":{"GB2-01":1739.0114851123444,"GB2-02":1413.3571447074532,"GB2-03":1375.2619874653299,"GB2-04":1391.971331282551,"GB2-05":1766.2684251914866,"GB2-06":1834.422702351709,"GB2-07":1684.7963698508281,"GB2-08":1931.433559611224}},"per_game_tracks":{"highest":{"GB2-01":73.84725078211831,"GB2-02":59.21782579520304,"GB2-03":68.91099828064931,"GB2-04":85.53702993381843,"GB2-05":52.95569071867738,"GB2-06":84.1691849172907,"GB2-07":61.26424951289066,"GB2-08":35.23351331310822},"medium":{"GB2-01":56.519674933057175,"GB2-02":36.08336866932161,"GB2-03":13.925660427832574,"GB2-04":27.320051355957688,"GB2-05":66.74309410747507,"GB2-06":74.90758169037487,"GB2-07":66.61852060343541,"GB2-08":83.86890130218805},"none":{"GB2-01":61.0616104086017,"GB2-02":8.30135369548809,"GB2-03":25.909155462658255,"GB2-04":10.302860861924804,"GB2-05":66.07585031971833,"GB2-06":70.71820370255907,"GB2-07":59.62572675932049,"GB2-08":70.75317794233399}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":65.1419679067195,"medium":53.2483566362053,"none":46.59349239407559},"reasoning_agg":{"highest":{"max":85.53702993381843,"mean":65.1419679067195,"min":35.23351331310822},"medium":{"max":83.86890130218805,"mean":53.2483566362053,"min":13.925660427832574},"none":{"max":70.75317794233399,"mean":46.59349239407559,"min":8.30135369548809}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":85.53702993381843,"expected_score":55.419640339540024,"reasoning_variance":18.54847551264391,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.4250346938732221},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":85.53702993381843,"expected_score":60.492464219515966,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.649503687203534},"medium":{"ceiling_score":83.86890130218805,"expected_score":55.428049758343796,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.179693122138495},"none":{"ceiling_score":70.75317794233399,"expected_score":50.33840704076032,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.744914646684734}}},{"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":1.872758},"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":1.8727580000000001}},"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":47.70725999383138,"highest":52.89362205123531,"medium":57.76474815367045,"none":32.46340977658835},"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":"2026-09-25T15:19:40Z","match_totals_all":{"draws":1842,"losses":1934,"wins":2719},"match_totals_tracks":{"highest":{"draws":572,"losses":614,"wins":1031},"medium":{"draws":411,"losses":451,"wins":1070},"none":{"draws":859,"losses":869,"wins":618}},"model_slug":"x-ai-grok-4-6","overall":{"max":80.29583807622168,"mean":47.70725999383137,"min":12.14033355812917},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":10,"overall_ranking_status":"ranked","per_game":{"GB2-01":44.46326454223426,"GB2-02":61.09063610309277,"GB2-03":36.55815458856067,"GB2-04":34.57744830171936,"GB2-05":80.29583807622168,"GB2-06":63.03521018257703,"GB2-07":70.75695908292762,"GB2-08":32.37146553254912},"per_game_all":{"GB2-01":48.06228298194488,"GB2-02":33.45825614163261,"GB2-03":41.5861865934885,"GB2-04":28.549291930530924,"GB2-05":69.51680290878441,"GB2-06":53.58261526885241,"GB2-07":62.72791025117982,"GB2-08":44.17473387423746},"per_game_match_totals_all":{"GB2-01":{"draws":272,"losses":247,"wins":317},"GB2-02":{"draws":398,"losses":97,"wins":216},"GB2-03":{"draws":350,"losses":197,"wins":233},"GB2-04":{"draws":430,"losses":207,"wins":219},"GB2-05":{"draws":0,"losses":226,"wins":532},"GB2-06":{"draws":55,"losses":390,"wins":319},"GB2-07":{"draws":0,"losses":310,"wins":562},"GB2-08":{"draws":337,"losses":260,"wins":321}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":168,"losses":73,"wins":75},"GB2-02":{"draws":37,"losses":26,"wins":164},"GB2-03":{"draws":81,"losses":112,"wins":121},"GB2-04":{"draws":137,"losses":82,"wins":101},"GB2-05":{"draws":0,"losses":32,"wins":202},"GB2-06":{"draws":25,"losses":114,"wins":113},"GB2-07":{"draws":0,"losses":75,"wins":185},"GB2-08":{"draws":124,"losses":100,"wins":70}},"medium":{"GB2-01":{"draws":69,"losses":80,"wins":87},"GB2-02":{"draws":160,"losses":38,"wins":42},"GB2-03":{"draws":59,"losses":58,"wins":111},"GB2-04":{"draws":99,"losses":49,"wins":94},"GB2-05":{"draws":0,"losses":45,"wins":187},"GB2-06":{"draws":24,"losses":48,"wins":164},"GB2-07":{"draws":0,"losses":80,"wins":180},"GB2-08":{"draws":0,"losses":53,"wins":205}},"none":{"GB2-01":{"draws":35,"losses":94,"wins":155},"GB2-02":{"draws":201,"losses":33,"wins":10},"GB2-03":{"draws":210,"losses":27,"wins":1},"GB2-04":{"draws":194,"losses":76,"wins":24},"GB2-05":{"draws":0,"losses":149,"wins":143},"GB2-06":{"draws":6,"losses":228,"wins":42},"GB2-07":{"draws":0,"losses":155,"wins":197},"GB2-08":{"draws":213,"losses":107,"wins":46}}},"per_game_raw_elo_all":{"GB2-01":1555.9776568714813,"GB2-02":1591.2647381161348,"GB2-03":1541.0160995691504,"GB2-04":1513.7071604821674,"GB2-05":1820.9856029643572,"GB2-06":1549.5664192523666,"GB2-07":1733.0240781757645,"GB2-08":1579.6423709534135},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1504.1969563117673,"GB2-02":1788.033141954644,"GB2-03":1485.1119937212918,"GB2-04":1552.2109146893276,"GB2-05":1993.0294584176775,"GB2-06":1706.161778721584,"GB2-07":1853.977814531143,"GB2-08":1424.473702042447},"medium":{"GB2-01":1569.8054293883342,"GB2-02":1529.649227789607,"GB2-03":1703.2849728497006,"GB2-04":1584.3811214442503,"GB2-05":1957.513704268975,"GB2-06":1897.9680555231073,"GB2-07":1837.9987970990019,"GB2-08":1927.6798227439356},"none":{"GB2-01":1593.9305849143425,"GB2-02":1456.1118446041532,"GB2-03":1434.6513321364587,"GB2-04":1404.529445312924,"GB2-05":1512.4136462064191,"GB2-06":1044.5694235124092,"GB2-07":1507.0956228971488,"GB2-08":1386.7735880738578}},"per_game_tracks":{"highest":{"GB2-01":44.46326454223426,"GB2-02":61.09063610309277,"GB2-03":36.55815458856067,"GB2-04":34.57744830171936,"GB2-05":80.29583807622168,"GB2-06":63.03521018257703,"GB2-07":70.75695908292762,"GB2-08":32.37146553254912},"medium":{"GB2-01":48.914921531324325,"GB2-02":24.805218937462044,"GB2-03":56.698811869129386,"GB2-04":38.93009393174424,"GB2-05":78.05231532268954,"GB2-06":74.56969734908822,"GB2-07":69.68601350315085,"GB2-08":70.46091278477508},"none":{"GB2-01":50.80866287227604,"GB2-02":14.478913384343024,"GB2-03":31.50159332277543,"GB2-04":12.14033355812917,"GB2-05":50.202255327441996,"GB2-06":23.142938274891982,"GB2-07":47.74075816746098,"GB2-08":29.691823305388205}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.89362205123531,"medium":57.76474815367045,"none":32.46340977658835},"reasoning_agg":{"highest":{"max":80.29583807622168,"mean":52.89362205123531,"min":32.37146553254912},"medium":{"max":78.05231532268954,"mean":57.76474815367045,"min":24.805218937462044},"none":{"max":50.80866287227604,"mean":32.46340977658835,"min":12.14033355812917}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":80.29583807622168,"expected_score":46.90898936028708,"reasoning_variance":25.301338377082104,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7982706335442913},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":80.29583807622168,"expected_score":45.69907996697321,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.194542084262103},"medium":{"ceiling_score":78.05231532268954,"expected_score":61.91754413978642,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.152795986115969},"none":{"ceiling_score":50.80866287227604,"expected_score":33.1103439741016,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.6469341975132537}}},{"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":0.7687025},"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":12.15224}},"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":15.187937499999997},"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":49.95190250586902,"highest":63.56633841927054,"medium":44.08690114479181,"none":35.34236797788512},"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":"2026-09-25T15:05:53Z","match_totals_all":{"draws":2190,"losses":2280,"wins":3487},"match_totals_tracks":{"highest":{"draws":374,"losses":480,"wins":1521},"medium":{"draws":900,"losses":780,"wins":1116},"none":{"draws":916,"losses":1020,"wins":850}},"model_slug":"gpt-5-4","overall":{"max":100.0,"mean":46.96953695880148,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":11,"overall_ranking_status":"ranked","per_game":{"GB2-01":90.9620272870252,"GB2-03":26.396024096701737,"GB2-04":40.38810520024291,"GB2-05":80.92593525080028,"GB2-06":74.94353809455754,"GB2-07":79.42432262453787,"GB2-08":51.92441638102823},"per_game_all":{"GB2-01":84.01825747598137,"GB2-03":25.698604678355792,"GB2-04":16.536085552068034,"GB2-05":67.29155661918192,"GB2-06":70.66075222580824,"GB2-07":49.02755832795966,"GB2-08":36.43050266172815},"per_game_match_totals_all":{"GB2-01":{"draws":33,"losses":83,"wins":834},"GB2-02":{"draws":516,"losses":84,"wins":27},"GB2-03":{"draws":491,"losses":362,"wins":216},"GB2-04":{"draws":524,"losses":287,"wins":170},"GB2-05":{"draws":0,"losses":276,"wins":688},"GB2-06":{"draws":71,"losses":237,"wins":694},"GB2-07":{"draws":0,"losses":568,"wins":576},"GB2-08":{"draws":555,"losses":383,"wins":282}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":6,"losses":14,"wins":290},"GB2-03":{"draws":137,"losses":142,"wins":110},"GB2-04":{"draws":163,"losses":47,"wins":102},"GB2-05":{"draws":0,"losses":34,"wins":290},"GB2-06":{"draws":26,"losses":54,"wins":250},"GB2-07":{"draws":0,"losses":62,"wins":282},"GB2-08":{"draws":42,"losses":127,"wins":197}},"medium":{"GB2-01":{"draws":5,"losses":4,"wins":307},"GB2-02":{"draws":265,"losses":48,"wins":20},"GB2-03":{"draws":188,"losses":109,"wins":69},"GB2-04":{"draws":158,"losses":114,"wins":30},"GB2-05":{"draws":0,"losses":94,"wins":218},"GB2-06":{"draws":23,"losses":64,"wins":249},"GB2-07":{"draws":0,"losses":227,"wins":153},"GB2-08":{"draws":261,"losses":120,"wins":70}},"none":{"GB2-01":{"draws":22,"losses":65,"wins":237},"GB2-02":{"draws":251,"losses":36,"wins":7},"GB2-03":{"draws":166,"losses":111,"wins":37},"GB2-04":{"draws":203,"losses":126,"wins":38},"GB2-05":{"draws":0,"losses":148,"wins":180},"GB2-06":{"draws":22,"losses":119,"wins":195},"GB2-07":{"draws":0,"losses":279,"wins":141},"GB2-08":{"draws":252,"losses":136,"wins":15}}},"per_game_raw_elo_all":{"GB2-01":2055.8909920384044,"GB2-03":1368.263154114793,"GB2-04":1432.5088656076111,"GB2-05":1782.709605225679,"GB2-06":1829.1215547926543,"GB2-07":1525.5130095319025,"GB2-08":1474.507553239927},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2152.9795477867438,"GB2-03":1374.71380781756,"GB2-04":1590.9896839264163,"GB2-05":1999.13038791591,"GB2-06":1900.1607633818742,"GB2-07":1980.0748987537597,"GB2-08":1679.5781289256847},"medium":{"GB2-01":2278.825931725217,"GB2-02":1457.226429295739,"GB2-03":1409.4553692437319,"GB2-04":1323.7909588152809,"GB2-05":1771.050242288496,"GB2-06":1881.963566228328,"GB2-07":1311.602479274004,"GB2-08":1426.3679003269972},"none":{"GB2-01":1735.867496603253,"GB2-02":1466.4655668165492,"GB2-03":1320.6202852830872,"GB2-04":1382.7459540811358,"GB2-05":1577.948185472631,"GB2-06":1705.2403347677614,"GB2-07":1284.8616505679433,"GB2-08":1317.5766304670988}},"per_game_tracks":{"highest":{"GB2-01":90.9620272870252,"GB2-03":26.396024096701737,"GB2-04":40.38810520024291,"GB2-05":80.92593525080028,"GB2-06":74.94353809455754,"GB2-07":79.42432262453787,"GB2-08":51.92441638102823},"medium":{"GB2-01":100.0,"GB2-02":15.152435531238186,"GB2-03":29.602746818470994,"GB2-04":0.0,"GB2-05":66.53681950526628,"GB2-06":73.85631875502746,"GB2-07":34.69185025593699,"GB2-08":32.85503829239455},"none":{"GB2-01":61.092745140918936,"GB2-02":16.25613376182144,"GB2-03":21.097043119894657,"GB2-04":9.220151455961185,"GB2-05":54.4119151014792,"GB2-06":63.18239982783971,"GB2-07":32.966502103404125,"GB2-08":24.51205331176168}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":61.479341753727496,"medium":44.08690114479181,"none":35.34236797788512},"reasoning_agg":{"highest":{"max":90.9620272870252,"mean":61.479341753727496,"min":26.396024096701737},"medium":{"max":100.0,"mean":44.08690114479181,"min":0.0},"none":{"max":63.18239982783971,"mean":35.34236797788512,"min":9.220151455961185}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":100.0,"expected_score":48.954236682330766,"reasoning_variance":26.136973775842378,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.984699723529289},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":90.9620272870252,"expected_score":58.08753735871808,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.391804395009416},"medium":{"ceiling_score":100.0,"expected_score":44.923001831584514,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.8361006867927046},"none":{"ceiling_score":63.18239982783971,"expected_score":37.12549901273732,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7831310348522038}}},{"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":0.11920932499999999},"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":0.029847899999999997},"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":0.19534587500000003},"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":46.89826236788541,"highest":50.8933219700669,"medium":54.61401951813503,"none":35.18744561545431},"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":"2026-09-25T14:25:14Z","match_totals_all":{"draws":1665,"losses":2100,"wins":2556},"match_totals_tracks":{"highest":{"draws":434,"losses":648,"wins":978},"medium":{"draws":527,"losses":647,"wins":939},"none":{"draws":704,"losses":805,"wins":639}},"model_slug":"z-ai-glm-5-3-flash","overall":{"max":73.9709651519967,"mean":46.898262367885415,"min":11.498805673082217},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":12,"overall_ranking_status":"ranked","per_game":{"GB2-01":57.23829261695304,"GB2-02":39.574682510188765,"GB2-03":62.99601875550448,"GB2-04":66.33514913196505,"GB2-05":73.82177341477453,"GB2-06":20.860857984814505,"GB2-07":65.67599407739836,"GB2-08":20.64380726893646},"per_game_all":{"GB2-01":52.18190259309302,"GB2-02":24.068402559966017,"GB2-03":51.79634379201207,"GB2-04":58.99559141602819,"GB2-05":56.9966784538654,"GB2-06":45.899836415549466,"GB2-07":65.6733093582629,"GB2-08":19.574034354306207},"per_game_match_totals_all":{"GB2-01":{"draws":162,"losses":297,"wins":373},"GB2-02":{"draws":509,"losses":98,"wins":129},"GB2-03":{"draws":193,"losses":204,"wins":324},"GB2-04":{"draws":197,"losses":141,"wins":408},"GB2-05":{"draws":0,"losses":369,"wins":435},"GB2-06":{"draws":62,"losses":416,"wins":338},"GB2-07":{"draws":0,"losses":265,"wins":525},"GB2-08":{"draws":542,"losses":310,"wins":24}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":2,"losses":101,"wins":201},"GB2-02":{"draws":121,"losses":25,"wins":88},"GB2-03":{"draws":54,"losses":61,"wins":129},"GB2-04":{"draws":47,"losses":35,"wins":156},"GB2-05":{"draws":0,"losses":73,"wins":171},"GB2-06":{"draws":9,"losses":181,"wins":46},"GB2-07":{"draws":0,"losses":93,"wins":185},"GB2-08":{"draws":201,"losses":79,"wins":2}},"medium":{"GB2-01":{"draws":7,"losses":90,"wins":133},"GB2-02":{"draws":185,"losses":45,"wins":24},"GB2-03":{"draws":61,"losses":56,"wins":118},"GB2-04":{"draws":55,"losses":61,"wins":152},"GB2-05":{"draws":0,"losses":171,"wins":149},"GB2-06":{"draws":22,"losses":52,"wins":172},"GB2-07":{"draws":0,"losses":77,"wins":175},"GB2-08":{"draws":197,"losses":95,"wins":16}},"none":{"GB2-01":{"draws":153,"losses":106,"wins":39},"GB2-02":{"draws":203,"losses":28,"wins":17},"GB2-03":{"draws":78,"losses":87,"wins":77},"GB2-04":{"draws":95,"losses":45,"wins":100},"GB2-05":{"draws":0,"losses":125,"wins":115},"GB2-06":{"draws":31,"losses":183,"wins":120},"GB2-07":{"draws":0,"losses":95,"wins":165},"GB2-08":{"draws":144,"losses":136,"wins":6}}},"per_game_raw_elo_all":{"GB2-01":1613.508840936682,"GB2-02":1524.1479164543543,"GB2-03":1650.4455240365423,"GB2-04":1716.9966816695471,"GB2-05":1621.4909799527386,"GB2-06":1421.7408931203754,"GB2-07":1777.9861430963422,"GB2-08":1256.02322057635},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1682.8213386192058,"GB2-02":1634.8527377787163,"GB2-03":1769.4036597862491,"GB2-04":1766.1518146573342,"GB2-05":1889.6822090150788,"GB2-06":1008.7351772149632,"GB2-07":1777.3553951311483,"GB2-08":1270.5083937551233},"medium":{"GB2-01":1795.3762702550496,"GB2-02":1491.8617465400573,"GB2-03":1702.8455834195784,"GB2-04":1795.060755450437,"GB2-05":1601.9190358488256,"GB2-06":1887.5237166831148,"GB2-07":1816.0959356058881,"GB2-08":1347.6593543617612},"none":{"GB2-01":1362.3289139357905,"GB2-02":1445.7292650442894,"GB2-03":1479.0873289037993,"GB2-04":1589.7774749008704,"GB2-05":1372.8716949943114,"GB2-06":1368.963785463048,"GB2-07":1740.5070985519903,"GB2-08":1149.9019136121656}},"per_game_tracks":{"highest":{"GB2-01":57.23829261695304,"GB2-02":39.574682510188765,"GB2-03":62.99601875550448,"GB2-04":66.33514913196505,"GB2-05":73.82177341477453,"GB2-06":20.860857984814505,"GB2-07":65.67599407739836,"GB2-08":20.64380726893646},"medium":{"GB2-01":65.06310136370395,"GB2-02":19.58473584796164,"GB2-03":56.69463597353327,"GB2-04":70.92301827974818,"GB2-05":55.90420106515226,"GB2-06":73.9709651519967,"GB2-07":68.19200834208425,"GB2-08":26.579490120899948},"none":{"GB2-01":34.24431379862208,"GB2-02":13.04578932174765,"GB2-03":35.69837664699844,"GB2-04":39.72860683637134,"GB2-05":41.264060881669415,"GB2-06":42.867686109837216,"GB2-07":63.151925655306094,"GB2-08":11.498805673082217}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.8933219700669,"medium":54.61401951813503,"none":35.18744561545431},"reasoning_agg":{"highest":{"max":73.82177341477453,"mean":50.8933219700669,"min":20.64380726893646},"medium":{"max":73.9709651519967,"mean":54.61401951813503,"min":19.58473584796164},"none":{"max":63.151925655306094,"mean":35.18744561545431,"min":11.498805673082217}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":73.9709651519967,"expected_score":45.672892019609215,"reasoning_variance":19.426573902680722,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.2253703482762006},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":73.82177341477453,"expected_score":43.14403583973492,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.749286130331981},"medium":{"ceiling_score":73.9709651519967,"expected_score":57.48653300658083,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.8725134884457972},"none":{"ceiling_score":63.151925655306094,"expected_score":36.38810721251189,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.2006615970575822}}},{"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":0.057513089999999996}},"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":0.4623291732},"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":59.63173372243593,"none":33.96387114069511},"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":"2026-09-25T13:57:09Z","match_totals_all":{"draws":276,"losses":381,"wins":533},"match_totals_tracks":{"medium":{"draws":108,"losses":51,"wins":305},"none":{"draws":168,"losses":330,"wins":228}},"model_slug":"xiaomi-mimo-v2-6-pro","overall":{"max":77.84906750984048,"mean":46.79780243156552,"min":3.415118568191135},"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":13,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":49,"losses":66,"wins":35},"GB2-02":{"draws":103,"losses":36,"wins":53},"GB2-03":{"draws":11,"losses":35,"wins":18},"GB2-04":{"draws":104,"losses":19,"wins":53},"GB2-05":{"draws":0,"losses":60,"wins":26},"GB2-06":{"draws":9,"losses":68,"wins":121},"GB2-07":{"draws":0,"losses":67,"wins":39},"GB2-08":{"draws":0,"losses":30,"wins":188}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":16,"losses":28,"wins":26},"GB2-02":{"draws":38,"losses":5,"wins":53},"GB2-04":{"draws":50,"losses":6,"wins":36},"GB2-06":{"draws":4,"losses":6,"wins":86},"GB2-08":{"draws":0,"losses":6,"wins":104}},"none":{"GB2-01":{"draws":33,"losses":38,"wins":9},"GB2-02":{"draws":65,"losses":31,"wins":0},"GB2-03":{"draws":11,"losses":35,"wins":18},"GB2-04":{"draws":54,"losses":13,"wins":17},"GB2-05":{"draws":0,"losses":60,"wins":26},"GB2-06":{"draws":5,"losses":62,"wins":35},"GB2-07":{"draws":0,"losses":67,"wins":39},"GB2-08":{"draws":0,"losses":24,"wins":84}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1464.5833168613892,"GB2-02":1737.3177663783688,"GB2-04":1691.7277889611023,"GB2-06":1932.532829336563,"GB2-08":2038.093778360589},"none":{"GB2-01":1408.4912292460306,"GB2-02":1392.6076019714485,"GB2-03":1393.8720480178501,"GB2-04":1506.0835524827144,"GB2-05":1313.7719737993527,"GB2-06":1496.1032066491546,"GB2-07":1399.2346624876882,"GB2-08":1765.1638806175774}},"per_game_tracks":{"medium":{"GB2-01":39.83045327654045,"GB2-02":51.95961453842323,"GB2-04":52.745857819297356,"GB2-06":75.77367546807812,"GB2-08":77.84906750984048},"none":{"GB2-01":36.02595884308104,"GB2-02":3.415118568191135,"GB2-03":25.43721144686283,"GB2-04":24.435827804187948,"GB2-05":36.46449004717655,"GB2-06":49.486251574367515,"GB2-07":39.3468858005456,"GB2-08":57.09922504114827}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":59.63173372243593,"none":33.96387114069511},"reasoning_agg":{"medium":{"max":77.84906750984048,"mean":59.63173372243593,"min":39.83045327654045},"none":{"max":57.09922504114827,"mean":33.96387114069511,"min":3.415118568191135}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":77.84906750984048,"reasoning_variance":25.66786258174082},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":77.84906750984048,"expected_score":65.2707873706737,"reliability_score":91.71416321055985,"uncertainty_avg":8.285836789440156,"uncertainty_penalty":5.63905364823777},"none":{"ceiling_score":57.09922504114827,"expected_score":37.338812135101236,"reliability_score":91.04086563438126,"uncertainty_avg":8.959134365618741,"uncertainty_penalty":3.374940994406124}}},{"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":0.25553343903391196}},"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":0.5746151281850016},"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":1.9756462499999996},"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":46.676617921107535,"highest":51.44019386589474,"medium":47.04816057368627,"none":41.5414993237416},"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":"2026-09-25T15:19:38Z","match_totals_all":{"draws":1558,"losses":2045,"wins":2843},"match_totals_tracks":{"highest":{"draws":341,"losses":655,"wins":1094},"medium":{"draws":650,"losses":647,"wins":858},"none":{"draws":567,"losses":743,"wins":891}},"model_slug":"google-gemini-3-8-flash","overall":{"max":83.10880420461697,"mean":46.67661792110753,"min":7.419192145713985},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":14,"overall_ranking_status":"ranked","per_game":{"GB2-01":45.63626796266691,"GB2-02":40.106142336092056,"GB2-03":59.606732398356996,"GB2-04":21.023257576979688,"GB2-05":63.744543854931486,"GB2-06":83.10880420461697,"GB2-07":61.419590951500844,"GB2-08":36.876211642013004},"per_game_all":{"GB2-01":51.21426903559947,"GB2-02":20.85257006026728,"GB2-03":55.81360244374772,"GB2-04":25.6590086097742,"GB2-05":54.52872495060358,"GB2-06":74.43582492753016,"GB2-07":50.931115687252706,"GB2-08":39.97782765408517},"per_game_match_totals_all":{"GB2-01":{"draws":191,"losses":291,"wins":414},"GB2-02":{"draws":490,"losses":95,"wins":108},"GB2-03":{"draws":157,"losses":178,"wins":421},"GB2-04":{"draws":317,"losses":238,"wins":188},"GB2-05":{"draws":0,"losses":375,"wins":419},"GB2-06":{"draws":52,"losses":165,"wins":499},"GB2-07":{"draws":0,"losses":416,"wins":490},"GB2-08":{"draws":351,"losses":287,"wins":304}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":134,"wins":161},"GB2-02":{"draws":97,"losses":35,"wins":104},"GB2-03":{"draws":23,"losses":64,"wins":144},"GB2-04":{"draws":36,"losses":107,"wins":90},"GB2-05":{"draws":0,"losses":97,"wins":145},"GB2-06":{"draws":22,"losses":34,"wins":178},"GB2-07":{"draws":0,"losses":100,"wins":164},"GB2-08":{"draws":142,"losses":84,"wins":108}},"medium":{"GB2-01":{"draws":31,"losses":71,"wins":134},"GB2-02":{"draws":195,"losses":28,"wins":2},"GB2-03":{"draws":62,"losses":19,"wins":157},"GB2-04":{"draws":155,"losses":61,"wins":60},"GB2-05":{"draws":0,"losses":122,"wins":112},"GB2-06":{"draws":17,"losses":54,"wins":173},"GB2-07":{"draws":0,"losses":164,"wins":200},"GB2-08":{"draws":190,"losses":128,"wins":20}},"none":{"GB2-01":{"draws":139,"losses":86,"wins":119},"GB2-02":{"draws":198,"losses":32,"wins":2},"GB2-03":{"draws":72,"losses":95,"wins":120},"GB2-04":{"draws":126,"losses":70,"wins":38},"GB2-05":{"draws":0,"losses":156,"wins":162},"GB2-06":{"draws":13,"losses":77,"wins":148},"GB2-07":{"draws":0,"losses":152,"wins":126},"GB2-08":{"draws":19,"losses":75,"wins":176}}},"per_game_raw_elo_all":{"GB2-01":1599.22214562458,"GB2-02":1502.0806424938162,"GB2-03":1692.6695523029966,"GB2-04":1496.2261646859442,"GB2-05":1582.4667092665425,"GB2-06":1895.6094767025531,"GB2-07":1556.559467789781,"GB2-08":1523.9869061595625},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1520.558062708041,"GB2-02":1638.5162560866765,"GB2-03":1734.0510593713882,"GB2-04":1466.2382047303836,"GB2-05":1729.7591306402276,"GB2-06":2039.456503193102,"GB2-07":1714.4722670576302,"GB2-08":1482.3669038906078},"medium":{"GB2-01":1718.9045844132177,"GB2-02":1461.09447306829,"GB2-03":1795.5667967296579,"GB2-04":1561.4731006614738,"GB2-05":1491.1599487804237,"GB2-06":1848.7427852132082,"GB2-07":1627.8857977812459,"GB2-08":1318.3303361458036},"none":{"GB2-01":1558.2037897524815,"GB2-02":1406.631198326482,"GB2-03":1548.390800807944,"GB2-04":1460.9671886659755,"GB2-05":1526.481048378976,"GB2-06":1798.6291417013492,"GB2-07":1327.3203385304666,"GB2-08":1771.2634784422758}},"per_game_tracks":{"highest":{"GB2-01":45.63626796266691,"GB2-02":40.106142336092056,"GB2-03":59.606732398356996,"GB2-04":21.023257576979688,"GB2-05":63.744543854931486,"GB2-06":83.10880420461697,"GB2-07":61.419590951500844,"GB2-08":36.876211642013004},"medium":{"GB2-01":59.60452983725393,"GB2-02":15.032375698995798,"GB2-03":65.42521343604795,"GB2-04":35.71773602229773,"GB2-05":48.69228506640679,"GB2-06":71.62237123829571,"GB2-07":55.860008031893024,"GB2-08":24.43076525829919},"none":{"GB2-01":48.40200930687758,"GB2-02":7.419192145713985,"GB2-03":42.40886149683821,"GB2-04":20.23603223004519,"GB2-05":51.14934593047246,"GB2-06":68.57629933967782,"GB2-07":35.51374807836425,"GB2-08":58.62650606194331}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":51.44019386589474,"medium":47.04816057368627,"none":41.5414993237416},"reasoning_agg":{"highest":{"max":83.10880420461697,"mean":51.44019386589474,"min":21.023257576979688},"medium":{"max":71.62237123829571,"mean":47.04816057368627,"min":15.032375698995798},"none":{"max":68.57629933967782,"mean":41.5414993237416,"min":7.419192145713985}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":83.10880420461697,"expected_score":46.47222468200883,"reasoning_variance":9.898694542153144,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.20439323909869955},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":83.10880420461697,"expected_score":44.933576543311844,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.506617322582898},"medium":{"ceiling_score":71.62237123829571,"expected_score":49.657390901096136,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.6092303274098683},"none":{"ceiling_score":68.57629933967782,"expected_score":44.825706601618506,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.2842072778769094}}},{"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":0.5964052000000001},"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":0.5087455999999999},"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":0.5964052}},"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":1.6998543999999998},"codegen_latency_ms":{"attempt_count":34,"max_ms":187781,"mean_ms":106806.625,"min_ms":66051,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":11,"max_ms":187781,"mean_ms":116991.125,"min_ms":74353,"run_count":8},"medium":{"attempt_count":9,"max_ms":137371,"mean_ms":104700.625,"min_ms":79776,"run_count":8},"none":{"attempt_count":14,"max_ms":128385,"mean_ms":98728.125,"min_ms":66051,"run_count":8}},"codegen_output_tokens":{"attempt_count":34,"output_max":15570,"output_mean":7807.958333333333,"output_min":4284,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":11,"output_max":15570,"output_mean":8557.875,"output_min":4867,"run_count":8},"medium":{"attempt_count":9,"output_max":9385,"output_mean":7450.25,"output_min":5674,"run_count":8},"none":{"attempt_count":14,"output_max":10165,"output_mean":7415.75,"output_min":4284,"run_count":8}},"display_name":"Grok 4.5","economics":{"all":45.660755579671516,"highest":51.011009449206256,"medium":48.89069299775914,"none":37.08056429204913},"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":"2026-09-25T16:16:29Z","match_totals_all":{"draws":1983,"losses":2538,"wins":3740},"match_totals_tracks":{"highest":{"draws":589,"losses":885,"wins":1707},"medium":{"draws":425,"losses":501,"wins":880},"none":{"draws":969,"losses":1152,"wins":1153}},"model_slug":"x-ai-grok-4-5","overall":{"max":79.71896425856343,"mean":45.66075557967151,"min":0.0},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":15,"overall_ranking_status":"ranked","per_game":{"GB2-01":74.32458663155238,"GB2-02":34.977282075387954,"GB2-03":25.104629327422128,"GB2-04":22.083742425713893,"GB2-05":69.76004691232554,"GB2-06":50.814135198615915,"GB2-07":51.304688764068835,"GB2-08":79.71896425856343},"per_game_all":{"GB2-01":65.26450047267409,"GB2-02":24.066537291754738,"GB2-03":21.5979234918818,"GB2-04":16.711401388890625,"GB2-05":61.17525971050247,"GB2-06":47.51097922825924,"GB2-07":57.3397175476776,"GB2-08":71.61972550573154},"per_game_match_totals_all":{"GB2-01":{"draws":346,"losses":186,"wins":513},"GB2-02":{"draws":637,"losses":145,"wins":169},"GB2-03":{"draws":300,"losses":404,"wins":161},"GB2-04":{"draws":607,"losses":212,"wins":145},"GB2-05":{"draws":0,"losses":365,"wins":592},"GB2-06":{"draws":85,"losses":624,"wins":548},"GB2-07":{"draws":0,"losses":442,"wins":694},"GB2-08":{"draws":8,"losses":160,"wins":918}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":75,"losses":36,"wins":271},"GB2-02":{"draws":182,"losses":55,"wins":115},"GB2-03":{"draws":150,"losses":115,"wins":88},"GB2-04":{"draws":155,"losses":114,"wins":93},"GB2-05":{"draws":0,"losses":93,"wins":267},"GB2-06":{"draws":23,"losses":225,"wins":238},"GB2-07":{"draws":0,"losses":201,"wins":277},"GB2-08":{"draws":4,"losses":46,"wins":358}},"medium":{"GB2-01":{"draws":10,"losses":29,"wins":141},"GB2-02":{"draws":159,"losses":38,"wins":35},"GB2-03":{"draws":60,"losses":38,"wins":52},"GB2-04":{"draws":173,"losses":40,"wins":25},"GB2-05":{"draws":0,"losses":68,"wins":130},"GB2-06":{"draws":19,"losses":152,"wins":111},"GB2-07":{"draws":0,"losses":109,"wins":153},"GB2-08":{"draws":4,"losses":27,"wins":233}},"none":{"GB2-01":{"draws":261,"losses":121,"wins":101},"GB2-02":{"draws":296,"losses":52,"wins":19},"GB2-03":{"draws":90,"losses":251,"wins":21},"GB2-04":{"draws":279,"losses":58,"wins":27},"GB2-05":{"draws":0,"losses":204,"wins":195},"GB2-06":{"draws":43,"losses":247,"wins":199},"GB2-07":{"draws":0,"losses":132,"wins":264},"GB2-08":{"draws":0,"losses":87,"wins":327}}},"per_game_raw_elo_all":{"GB2-01":1794.6515363662602,"GB2-02":1521.419704656364,"GB2-03":1328.347019911811,"GB2-04":1434.125383733786,"GB2-05":1686.4344327612714,"GB2-06":1443.9774877947523,"GB2-07":1650.0324598796908,"GB2-08":1939.415249371522},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1918.6768759763554,"GB2-02":1597.403733556461,"GB2-03":1361.9795528555346,"GB2-04":1468.1095908237608,"GB2-05":1820.6789072396662,"GB2-06":1496.8009322240273,"GB2-07":1557.2577772164589,"GB2-08":2044.5328342692478},"medium":{"GB2-01":1895.2687657071344,"GB2-02":1547.9709614984808,"GB2-03":1528.4368423578528,"GB2-04":1448.7623936685657,"GB2-05":1727.6211599463707,"GB2-06":1409.2944605339005,"GB2-07":1597.2940888111907,"GB2-08":1941.3225089503185},"none":{"GB2-01":1570.0089674152905,"GB2-02":1418.8844189141503,"GB2-03":1094.6246645220451,"GB2-04":1385.504166709032,"GB2-05":1511.0032310977772,"GB2-06":1425.8370706263297,"GB2-07":1795.5455136114233,"GB2-08":1832.3904048949994}},"per_game_tracks":{"highest":{"GB2-01":74.32458663155238,"GB2-02":34.977282075387954,"GB2-03":25.104629327422128,"GB2-04":22.083742425713893,"GB2-05":69.76004691232554,"GB2-06":50.814135198615915,"GB2-07":51.304688764068835,"GB2-08":79.71896425856343},"medium":{"GB2-01":71.98011275701009,"GB2-02":27.323646009270874,"GB2-03":39.68914114822327,"GB2-04":18.426880670928522,"GB2-05":63.4401888214157,"GB2-06":45.187462067298945,"GB2-07":53.55982608465452,"GB2-08":71.51828642327122},"none":{"GB2-01":49.48880202945978,"GB2-02":9.898683790605384,"GB2-03":0.0,"GB2-04":9.623581070029456,"GB2-05":50.325543397766175,"GB2-06":46.531340418862875,"GB2-07":67.15463779430945,"GB2-08":63.62192583535994}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":51.011009449206256,"medium":48.89069299775914,"none":37.08056429204913},"reasoning_agg":{"highest":{"max":79.71896425856343,"mean":51.011009449206256,"min":22.083742425713893},"medium":{"max":71.98011275701009,"mean":48.89069299775914,"min":18.426880670928522},"none":{"max":67.15463779430945,"mean":37.08056429204913,"min":0.0}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":79.71896425856343,"expected_score":44.23887046582664,"reasoning_variance":13.930445157157124,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.4218851138448656},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":79.71896425856343,"expected_score":44.002701653974626,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.00830779523163},"medium":{"ceiling_score":71.98011275701009,"expected_score":50.72504001061407,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.8343470128549342},"none":{"ceiling_score":67.15463779430945,"expected_score":37.988869732891224,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.9083054408420921}}},{"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":1.30663125},"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":0.41740125},"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":0.19110975000000002}},"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":1.9151422500000002},"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":46.324142308221894,"highest":54.58231057179747,"medium":50.63974829395818,"none":31.068787453123537},"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":"2026-09-25T15:54:55Z","match_totals_all":{"draws":1333,"losses":1896,"wins":2520},"match_totals_tracks":{"highest":{"draws":300,"losses":386,"wins":803},"medium":{"draws":321,"losses":680,"wins":1097},"none":{"draws":712,"losses":830,"wins":620}},"model_slug":"meta-muse-spark-1-3","overall":{"max":78.27779768942712,"mean":45.43028210629307,"min":13.707425405221867},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":16,"overall_ranking_status":"partial","per_game":{"GB2-01":66.39429069545992,"GB2-02":16.539487456961396,"GB2-03":50.32890841701454,"GB2-06":77.02031061725003,"GB2-07":53.837866826293656,"GB2-08":63.37299941780524},"per_game_all":{"GB2-01":50.906801006353724,"GB2-02":19.784673079530563,"GB2-03":42.292801556650964,"GB2-06":67.48267388458765,"GB2-07":46.14216098007508,"GB2-08":51.335743342133334},"per_game_match_totals_all":{"GB2-01":{"draws":72,"losses":272,"wins":366},"GB2-02":{"draws":540,"losses":108,"wins":84},"GB2-03":{"draws":202,"losses":253,"wins":326},"GB2-04":{"draws":255,"losses":115,"wins":122},"GB2-05":{"draws":0,"losses":296,"wins":272},"GB2-06":{"draws":46,"losses":224,"wins":506},"GB2-07":{"draws":0,"losses":426,"wins":424},"GB2-08":{"draws":218,"losses":202,"wins":420}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":1,"losses":59,"wins":172},"GB2-02":{"draws":191,"losses":41,"wins":22},"GB2-03":{"draws":84,"losses":55,"wins":92},"GB2-06":{"draws":23,"losses":37,"wins":186},"GB2-07":{"draws":0,"losses":136,"wins":130},"GB2-08":{"draws":1,"losses":58,"wins":201}},"medium":{"GB2-01":{"draws":0,"losses":80,"wins":160},"GB2-02":{"draws":152,"losses":30,"wins":46},"GB2-03":{"draws":43,"losses":99,"wins":106},"GB2-04":{"draws":100,"losses":57,"wins":89},"GB2-05":{"draws":0,"losses":134,"wins":134},"GB2-06":{"draws":11,"losses":56,"wins":191},"GB2-07":{"draws":0,"losses":155,"wins":171},"GB2-08":{"draws":15,"losses":69,"wins":200}},"none":{"GB2-01":{"draws":71,"losses":133,"wins":34},"GB2-02":{"draws":197,"losses":37,"wins":16},"GB2-03":{"draws":75,"losses":99,"wins":128},"GB2-04":{"draws":155,"losses":58,"wins":33},"GB2-05":{"draws":0,"losses":162,"wins":138},"GB2-06":{"draws":12,"losses":131,"wins":129},"GB2-07":{"draws":0,"losses":135,"wins":123},"GB2-08":{"draws":202,"losses":75,"wins":19}}},"per_game_raw_elo_all":{"GB2-01":1597.5537935513084,"GB2-02":1493.8090087236312,"GB2-03":1548.4490247080437,"GB2-06":1779.4870597633492,"GB2-07":1485.7720885717324,"GB2-08":1674.8333366939578},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1813.8305646022727,"GB2-02":1470.2377075518823,"GB2-03":1635.343723849433,"GB2-06":1938.01034564622,"GB2-07":1601.257134738404,"GB2-08":1834.236180208509},"medium":{"GB2-01":1734.759712457236,"GB2-02":1539.6620961166543,"GB2-03":1484.4157889641933,"GB2-04":1562.6391068559133,"GB2-05":1586.9576519998002,"GB2-06":1958.2333885274027,"GB2-07":1512.883430442997,"GB2-08":1856.555157626162},"none":{"GB2-01":1244.071103594417,"GB2-02":1471.5272225023564,"GB2-03":1525.5875613105047,"GB2-04":1417.0738254576515,"GB2-05":1399.4470525560284,"GB2-06":1442.2174451164249,"GB2-07":1343.1757005337963,"GB2-08":1333.7086722472022}},"per_game_tracks":{"highest":{"GB2-01":66.39429069545992,"GB2-02":16.539487456961396,"GB2-03":50.32890841701454,"GB2-06":77.02031061725003,"GB2-07":53.837866826293656,"GB2-08":63.37299941780524},"medium":{"GB2-01":60.756781153993344,"GB2-02":26.121442848759003,"GB2-03":36.22845180963232,"GB2-04":35.67974117462816,"GB2-05":54.832172172826105,"GB2-06":78.27779768942712,"GB2-07":48.07302698639267,"GB2-08":65.14857251600664},"none":{"GB2-01":25.569331169607917,"GB2-02":16.693088932871294,"GB2-03":40.321044443306036,"GB2-04":13.707425405221867,"GB2-05":43.108249106768326,"GB2-06":47.149913347085835,"GB2-07":36.51558912753892,"GB2-08":25.485658092588114}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.58231057179747,"medium":50.63974829395818,"none":31.068787453123537},"reasoning_agg":{"highest":{"max":77.02031061725003,"mean":54.58231057179747,"min":16.539487456961396},"medium":{"max":78.27779768942712,"mean":50.63974829395818,"min":26.121442848759003},"none":{"max":47.149913347085835,"mean":31.068787453123537,"min":13.707425405221867}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":78.27779768942712,"expected_score":45.64876039864589,"reasoning_variance":23.513523118673934,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.21847829235282035},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.02031061725003,"expected_score":48.62304903578546,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.959261536012008},"medium":{"ceiling_score":78.27779768942712,"expected_score":53.130447691869904,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.490699397911726},"none":{"ceiling_score":47.149913347085835,"expected_score":32.177313240082114,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.1085257869585767}}},{"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":0.9693815250000001},"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":1.0866157440000002},"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":0.127518125},"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":0.9693815250000001}},"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":46.33649096115204,"highest":52.067151128510105,"medium":49.77163099580157,"none":35.083880829330376},"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":"2026-09-25T16:20:00Z","match_totals_all":{"draws":1643,"losses":2037,"wins":2567},"match_totals_tracks":{"highest":{"draws":606,"losses":595,"wins":967},"medium":{"draws":310,"losses":648,"wins":961},"none":{"draws":727,"losses":794,"wins":639}},"model_slug":"tencent-hy4-preview","overall":{"max":81.28231996103942,"mean":45.09619040783053,"min":9.957083818816807},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":17,"overall_ranking_status":"ranked","per_game":{"GB2-01":49.15370367716753,"GB2-02":61.51065884687536,"GB2-03":48.95177486372414,"GB2-04":31.959581269225342,"GB2-05":57.22864455350476,"GB2-06":77.83883887689821,"GB2-07":65.23965370756527,"GB2-08":24.654353233120247},"per_game_all":{"GB2-01":44.53026052791078,"GB2-03":43.01141942198788,"GB2-04":19.765271046312403,"GB2-05":52.94424353909823,"GB2-06":61.37637017521115,"GB2-07":59.646113422914055,"GB2-08":43.081758594629754},"per_game_match_totals_all":{"GB2-01":{"draws":223,"losses":371,"wins":324},"GB2-02":{"draws":284,"losses":42,"wins":176},"GB2-03":{"draws":261,"losses":192,"wins":242},"GB2-04":{"draws":430,"losses":158,"wins":108},"GB2-05":{"draws":0,"losses":417,"wins":463},"GB2-06":{"draws":38,"losses":309,"wins":491},"GB2-07":{"draws":0,"losses":327,"wins":501},"GB2-08":{"draws":407,"losses":221,"wins":262}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":162,"losses":73,"wins":83},"GB2-02":{"draws":75,"losses":17,"wins":170},"GB2-03":{"draws":23,"losses":69,"wins":136},"GB2-04":{"draws":115,"losses":52,"wins":75},"GB2-05":{"draws":0,"losses":100,"wins":136},"GB2-06":{"draws":17,"losses":54,"wins":175},"GB2-07":{"draws":0,"losses":115,"wins":177},"GB2-08":{"draws":214,"losses":115,"wins":15}},"medium":{"GB2-01":{"draws":15,"losses":141,"wins":134},"GB2-03":{"draws":147,"losses":53,"wins":27},"GB2-04":{"draws":140,"losses":68,"wins":16},"GB2-05":{"draws":0,"losses":150,"wins":166},"GB2-06":{"draws":8,"losses":141,"wins":193},"GB2-07":{"draws":0,"losses":67,"wins":195},"GB2-08":{"draws":0,"losses":28,"wins":230}},"none":{"GB2-01":{"draws":46,"losses":157,"wins":107},"GB2-02":{"draws":209,"losses":25,"wins":6},"GB2-03":{"draws":91,"losses":70,"wins":79},"GB2-04":{"draws":175,"losses":38,"wins":17},"GB2-05":{"draws":0,"losses":167,"wins":161},"GB2-06":{"draws":13,"losses":114,"wins":123},"GB2-07":{"draws":0,"losses":145,"wins":129},"GB2-08":{"draws":193,"losses":78,"wins":17}}},"per_game_raw_elo_all":{"GB2-01":1505.5071927892875,"GB2-03":1557.4611107106768,"GB2-04":1457.9702164572618,"GB2-05":1556.0891923279003,"GB2-06":1677.6483785334676,"GB2-07":1687.4907386982934,"GB2-08":1565.5464755739752},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1569.5488822308891,"GB2-02":1789.1900957382898,"GB2-03":1620.8637733818819,"GB2-04":1538.201890822483,"GB2-05":1626.6083808764358,"GB2-06":1951.562346562994,"GB2-07":1770.265865183308,"GB2-08":1321.0852609664673},"medium":{"GB2-01":1507.2996642393953,"GB2-03":1405.637968070786,"GB2-04":1393.4433122904995,"GB2-05":1541.0068505036463,"GB2-06":1661.9656968929207,"GB2-07":1860.3495757977012,"GB2-08":2070.1983831672133},"none":{"GB2-01":1439.673031897578,"GB2-02":1431.8518167627578,"GB2-03":1645.8815906793627,"GB2-04":1442.2654462588032,"GB2-05":1500.652345603618,"GB2-06":1419.4170921444886,"GB2-07":1431.8567751138708,"GB2-08":1305.355782588245}},"per_game_tracks":{"highest":{"GB2-01":49.15370367716753,"GB2-02":61.51065884687536,"GB2-03":48.95177486372414,"GB2-04":31.959581269225342,"GB2-05":57.22864455350476,"GB2-06":77.83883887689821,"GB2-07":65.23965370756527,"GB2-08":24.654353233120247},"medium":{"GB2-01":44.61529521482249,"GB2-03":28.716557872593558,"GB2-04":9.957083818816807,"GB2-05":52.05961783013132,"GB2-06":60.58021342324713,"GB2-07":71.19032884996027,"GB2-08":81.28231996103942},"none":{"GB2-01":39.82178269174233,"GB2-02":11.032703602266714,"GB2-03":51.36592552964594,"GB2-04":17.37914805089505,"GB2-05":49.5444682336586,"GB2-06":45.71005822548814,"GB2-07":42.508357711216625,"GB2-08":23.308602589729603}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.067151128510105,"medium":48.13753926565109,"none":35.083880829330376},"reasoning_agg":{"highest":{"max":77.83883887689821,"mean":52.067151128510105,"min":24.654353233120247},"medium":{"max":81.28231996103942,"mean":48.13753926565109,"min":9.957083818816807},"none":{"max":51.36592552964594,"mean":35.083880829330376,"min":11.032703602266714}},"reasoning_labels":{"highest":"High","medium":"Low","none":"None"},"reasoning_settings":{"balanced":"low","baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":81.28231996103942,"expected_score":44.74693705088425,"reasoning_variance":16.98327029917973,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.3492533569462779},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":77.83883887689821,"expected_score":45.06457954559386,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.0025715829162465},"medium":{"ceiling_score":81.28231996103942,"expected_score":51.7330251718938,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.5954859062427076},"none":{"ceiling_score":51.36592552964594,"expected_score":36.58923965624283,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.505358826912456}}},{"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":1.7435250000000002},"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":1.743525},"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":1.262825},"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":7.44989}},"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":10.456240000000001},"codegen_latency_ms":{"attempt_count":25,"max_ms":604929,"mean_ms":175315.375,"min_ms":28646,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":9,"max_ms":604929,"mean_ms":421376.5,"min_ms":132563,"run_count":8},"medium":{"attempt_count":8,"max_ms":137577,"mean_ms":68957.5,"min_ms":35597,"run_count":8},"none":{"attempt_count":8,"max_ms":48121,"mean_ms":35612.125,"min_ms":28646,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":52366,"output_mean":14843.708333333334,"output_min":2908,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":9,"output_max":52366,"output_mean":34524.125,"output_min":11990,"run_count":8},"medium":{"attempt_count":8,"output_max":11318,"output_mean":6205.25,"output_min":3583,"run_count":8},"none":{"attempt_count":8,"output_max":5116,"output_mean":3801.75,"output_min":2908,"run_count":8}},"display_name":"Claude Opus 4.8","economics":{"all":45.388157821566985,"highest":60.64361772447914,"medium":38.05563536159708,"none":35.51231631187023},"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":"2026-09-25T15:52:48Z","match_totals_all":{"draws":1281,"losses":1329,"wins":2164},"match_totals_tracks":{"highest":{"draws":203,"losses":305,"wins":970},"medium":{"draws":668,"losses":492,"wins":616},"none":{"draws":410,"losses":532,"wins":578}},"model_slug":"claude-opus-4-8","overall":{"max":78.12478117978807,"mean":43.68486599242672,"min":9.918422916272286},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":18,"overall_ranking_status":"ranked","per_game":{"GB2-01":65.07517251306582,"GB2-02":55.64032909915444,"GB2-04":34.48092158803702,"GB2-05":52.42649291219306,"GB2-06":78.12478117978807,"GB2-07":68.3072563481697,"GB2-08":70.45037043094591},"per_game_all":{"GB2-01":49.282309606742935,"GB2-02":25.5986103009426,"GB2-04":20.44428173382118,"GB2-05":43.143889098104204,"GB2-06":66.3809997787868,"GB2-07":59.93237099045498,"GB2-08":52.9346432421162},"per_game_match_totals_all":{"GB2-01":{"draws":117,"losses":177,"wins":300},"GB2-02":{"draws":466,"losses":74,"wins":142},"GB2-03":{"draws":80,"losses":53,"wins":23},"GB2-04":{"draws":425,"losses":106,"wins":113},"GB2-05":{"draws":0,"losses":339,"wins":295},"GB2-06":{"draws":32,"losses":162,"wins":418},"GB2-07":{"draws":0,"losses":226,"wins":488},"GB2-08":{"draws":161,"losses":192,"wins":385}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":25,"losses":42,"wins":127},"GB2-02":{"draws":82,"losses":3,"wins":131},"GB2-04":{"draws":86,"losses":26,"wins":92},"GB2-05":{"draws":0,"losses":103,"wins":113},"GB2-06":{"draws":10,"losses":19,"wins":151},"GB2-07":{"draws":0,"losses":57,"wins":173},"GB2-08":{"draws":0,"losses":55,"wins":183}},"medium":{"GB2-01":{"draws":50,"losses":77,"wins":91},"GB2-02":{"draws":202,"losses":34,"wins":2},"GB2-03":{"draws":80,"losses":53,"wins":23},"GB2-04":{"draws":175,"losses":41,"wins":10},"GB2-05":{"draws":0,"losses":101,"wins":119},"GB2-06":{"draws":1,"losses":32,"wins":173},"GB2-07":{"draws":0,"losses":69,"wins":185},"GB2-08":{"draws":160,"losses":85,"wins":13}},"none":{"GB2-01":{"draws":42,"losses":58,"wins":82},"GB2-02":{"draws":182,"losses":37,"wins":9},"GB2-04":{"draws":164,"losses":39,"wins":11},"GB2-05":{"draws":0,"losses":135,"wins":63},"GB2-06":{"draws":21,"losses":111,"wins":94},"GB2-07":{"draws":0,"losses":100,"wins":130},"GB2-08":{"draws":1,"losses":52,"wins":189}}},"per_game_raw_elo_all":{"GB2-01":1577.3612969395192,"GB2-02":1536.0035519855307,"GB2-04":1463.5090122428446,"GB2-05":1404.4293810786955,"GB2-06":1764.436254147932,"GB2-07":1693.605468934622,"GB2-08":1697.4659291651114},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1797.8711663723197,"GB2-02":1749.994117056542,"GB2-04":1557.1828199120182,"GB2-05":1551.5204169498527,"GB2-06":1960.5769388316662,"GB2-07":1818.9857739328693,"GB2-08":1928.5600377863639},"medium":{"GB2-01":1449.627713228418,"GB2-02":1433.4106515911064,"GB2-03":1364.9903528332513,"GB2-04":1436.8785480714125,"GB2-05":1484.663742536622,"GB2-06":1919.2834556174316,"GB2-07":1779.0511817326906,"GB2-08":1294.3553301644727},"none":{"GB2-01":1484.5850112178202,"GB2-02":1424.6058873089435,"GB2-04":1396.4656687451038,"GB2-05":1177.1039837496114,"GB2-06":1413.4483679946977,"GB2-07":1482.779451138306,"GB2-08":1869.4824195444983}},"per_game_tracks":{"highest":{"GB2-01":65.07517251306582,"GB2-02":55.64032909915444,"GB2-04":34.48092158803702,"GB2-05":52.42649291219306,"GB2-06":78.12478117978807,"GB2-07":68.3072563481697,"GB2-08":70.45037043094591},"medium":{"GB2-01":40.223782013343296,"GB2-02":11.23707888740107,"GB2-03":24.38530689431558,"GB2-04":16.531176212156833,"GB2-05":48.23196258690973,"GB2-06":75.74725395578018,"GB2-07":65.71581777847483,"GB2-08":22.372704564395118},"none":{"GB2-01":42.54797429381968,"GB2-02":9.918422916272286,"GB2-04":10.320747401269687,"GB2-05":28.773211795209818,"GB2-06":45.27096420079218,"GB2-07":45.77403884472038,"GB2-08":65.98085473100755}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":58.652579210624985,"medium":38.05563536159708,"none":34.34638340505811},"reasoning_agg":{"highest":{"max":78.12478117978807,"mean":58.652579210624985,"min":34.48092158803702},"medium":{"max":75.74725395578018,"mean":38.05563536159708,"min":11.23707888740107},"none":{"max":65.98085473100755,"mean":34.34638340505811,"min":9.918422916272286}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking field omitted"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":78.12478117978807,"expected_score":44.88173809777252,"reasoning_variance":24.306195805566873,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.196872105345797},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":78.12478117978807,"expected_score":56.40016525731385,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.252413953311134},"medium":{"ceiling_score":75.74725395578018,"expected_score":38.50757016549071,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.4519348038936286},"none":{"ceiling_score":65.98085473100755,"expected_score":36.78305964874749,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.4366762436893765}}},{"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":7.63796235},"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":0.8934513000000001}},"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":12.701101349999998},"codegen_latency_ms":{"attempt_count":122,"max_ms":348942,"mean_ms":136127.20833333334,"min_ms":17298,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":49,"max_ms":348942,"mean_ms":238985.4375,"min_ms":149523,"run_count":16},"medium":{"attempt_count":44,"max_ms":261708,"mean_ms":136549.0,"min_ms":44747,"run_count":16},"none":{"attempt_count":29,"max_ms":50160,"mean_ms":32847.1875,"min_ms":17298,"run_count":16}},"codegen_output_tokens":{"attempt_count":126,"output_max":100087,"output_mean":32301.520833333332,"output_min":2060,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":53,"output_max":100087,"output_mean":61701.5625,"output_min":36597,"run_count":16},"medium":{"attempt_count":44,"output_max":63652,"output_mean":30566.4375,"output_min":8874,"run_count":16},"none":{"attempt_count":29,"output_max":7962,"output_mean":4636.5625,"output_min":2060,"run_count":16}},"display_name":"Gemini 3.6 Flash","economics":{"all":47.17946049710128,"highest":56.14065082660016,"medium":45.26783194625648,"none":31.86715852062013},"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":"2026-09-25T15:41:54Z","match_totals_all":{"draws":4260,"losses":5278,"wins":6585},"match_totals_tracks":{"highest":{"draws":843,"losses":1263,"wins":2469},"medium":{"draws":1154,"losses":1421,"wins":2376},"none":{"draws":2263,"losses":2594,"wins":1740}},"model_slug":"google-gemini-3-6-flash","overall":{"max":84.32762532825016,"mean":42.63117632436954,"min":7.58639288876681},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":19,"overall_ranking_status":"ranked","per_game":{"GB2-01":48.08301890379797,"GB2-03":51.2458282828391,"GB2-04":41.20004663167366,"GB2-05":82.64092472785092,"GB2-06":84.32762532825016,"GB2-07":47.849290405989954,"GB2-08":37.63782150579934},"per_game_all":{"GB2-01":48.088897774886355,"GB2-03":42.96576058648935,"GB2-04":21.609339275249585,"GB2-05":66.91262964024556,"GB2-06":63.66994059673055,"GB2-07":46.67912007652867,"GB2-08":40.33053552957895},"per_game_match_totals_all":{"GB2-01":{"draws":681,"losses":801,"wins":708},"GB2-02":{"draws":806,"losses":108,"wins":9},"GB2-03":{"draws":413,"losses":682,"wins":754},"GB2-04":{"draws":1222,"losses":462,"wins":419},"GB2-05":{"draws":0,"losses":776,"wins":1651},"GB2-06":{"draws":181,"losses":791,"wins":1392},"GB2-07":{"draws":0,"losses":1017,"wins":1116},"GB2-08":{"draws":957,"losses":641,"wins":536}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":230,"losses":257,"wins":263},"GB2-03":{"draws":33,"losses":105,"wins":196},"GB2-04":{"draws":230,"losses":183,"wins":304},"GB2-05":{"draws":0,"losses":110,"wins":594},"GB2-06":{"draws":29,"losses":128,"wins":605},"GB2-07":{"draws":0,"losses":243,"wins":247},"GB2-08":{"draws":321,"losses":237,"wins":260}},"medium":{"GB2-01":{"draws":256,"losses":128,"wins":266},"GB2-02":{"draws":203,"losses":33,"wins":4},"GB2-03":{"draws":146,"losses":301,"wins":243},"GB2-04":{"draws":415,"losses":132,"wins":56},"GB2-05":{"draws":0,"losses":246,"wins":574},"GB2-06":{"draws":67,"losses":108,"wins":611},"GB2-07":{"draws":0,"losses":361,"wins":405},"GB2-08":{"draws":67,"losses":112,"wins":217}},"none":{"GB2-01":{"draws":195,"losses":416,"wins":179},"GB2-02":{"draws":603,"losses":75,"wins":5},"GB2-03":{"draws":234,"losses":276,"wins":315},"GB2-04":{"draws":577,"losses":147,"wins":59},"GB2-05":{"draws":0,"losses":420,"wins":483},"GB2-06":{"draws":85,"losses":555,"wins":176},"GB2-07":{"draws":0,"losses":413,"wins":464},"GB2-08":{"draws":569,"losses":292,"wins":59}}},"per_game_raw_elo_all":{"GB2-01":1553.820167116952,"GB2-03":1551.7553394723284,"GB2-04":1465.512559374661,"GB2-05":1774.372987637067,"GB2-06":1711.6579866658083,"GB2-07":1489.3778714900775,"GB2-08":1525.512419243064},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1552.8876848351229,"GB2-03":1640.6919382738752,"GB2-04":1594.8571569382302,"GB2-05":2025.4729516225789,"GB2-06":2054.014996548248,"GB2-07":1505.47687099777,"GB2-08":1490.2980039687752},"medium":{"GB2-01":1781.376438319557,"GB2-02":1411.8860565669552,"GB2-03":1496.108182778877,"GB2-04":1374.366983327068,"GB2-05":1762.7376902370997,"GB2-06":1933.1562045476744,"GB2-07":1443.9401740719447,"GB2-08":1754.109003622718},"none":{"GB2-01":1327.1963781961763,"GB2-02":1427.9983873981048,"GB2-03":1518.465897364233,"GB2-04":1427.3135378586849,"GB2-05":1534.9083210515219,"GB2-06":1147.8027589015026,"GB2-07":1518.7165694005175,"GB2-08":1332.1302501376986}},"per_game_tracks":{"highest":{"GB2-01":48.08301890379797,"GB2-03":51.2458282828391,"GB2-04":41.20004663167366,"GB2-05":82.64092472785092,"GB2-06":84.32762532825016,"GB2-07":47.849290405989954,"GB2-08":37.63782150579934},"medium":{"GB2-01":64.24089412492873,"GB2-02":8.220985627441877,"GB2-03":37.68882139766329,"GB2-04":7.58639288876681,"GB2-05":66.19105183427483,"GB2-06":77.04707674780836,"GB2-07":43.52282307590832,"GB2-08":57.64460987325958},"none":{"GB2-01":31.942780295932366,"GB2-02":11.07482345464506,"GB2-03":39.96263207896568,"GB2-04":16.041578305308295,"GB2-05":51.905912358610884,"GB2-06":29.63511971413311,"GB2-07":48.66524674768772,"GB2-08":25.70917520967793}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":52.24476245238841,"medium":43.7816080001001,"none":31.86715852062013},"reasoning_agg":{"highest":{"max":84.32762532825016,"mean":52.24476245238841,"min":37.63782150579934},"medium":{"max":77.04707674780836,"mean":43.7816080001001,"min":7.58639288876681},"none":{"max":51.905912358610884,"mean":31.86715852062013,"min":11.07482345464506}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":84.32762532825016,"expected_score":45.58648356114652,"reasoning_variance":20.377603931768277,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.9553072367769815},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":84.32762532825016,"expected_score":49.501046486279805,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.743715966108603},"medium":{"ceiling_score":77.04707674780836,"expected_score":46.825282518838925,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.0436745187388254},"none":{"ceiling_score":51.905912358610884,"expected_score":31.76686516364344,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.10029335697668884}}},{"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":42.384495360660594},"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":"2026-09-24T07:37:25Z","match_totals_all":{"draws":73,"losses":167,"wins":160},"match_totals_tracks":{"none":{"draws":73,"losses":167,"wins":160}},"model_slug":"gpt-4-1-nano","overall":{"max":42.384495360660594,"mean":42.384495360660594,"min":42.384495360660594},"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":20,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":73,"losses":167,"wins":160}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":73,"losses":167,"wins":160}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1472.7109953757326}},"per_game_tracks":{"none":{"GB2-01":42.384495360660594}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":42.384495360660594},"reasoning_agg":{"none":{"max":42.384495360660594,"mean":42.384495360660594,"min":42.384495360660594}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"Reasoning field omitted"},"reasoning_settings":{"baseline":"none"},"score_diagnostics":{"ceiling_score":42.384495360660594},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":42.384495360660594,"expected_score":44.81239740956288,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.4279020489022827}}},{"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":3.4542268568195333}},"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":42.3535558356776,"highest":55.185255291851604,"medium":33.29577520839935,"none":38.579637006781816},"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":"2026-09-25T14:20:11Z","match_totals_all":{"draws":1983,"losses":2125,"wins":2416},"match_totals_tracks":{"highest":{"draws":528,"losses":499,"wins":1015},"medium":{"draws":851,"losses":856,"wins":592},"none":{"draws":604,"losses":770,"wins":809}},"model_slug":"qwen-qwen3-8-2-4t-a95b","overall":{"max":81.83360524090116,"mean":42.35355583567759,"min":13.524183164803983},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":21,"overall_ranking_status":"ranked","per_game":{"GB2-01":45.61493415632901,"GB2-02":19.044287744530894,"GB2-03":70.85712897377837,"GB2-04":19.985371794844777,"GB2-05":63.23579274922259,"GB2-06":81.68122776333043,"GB2-07":59.229693911875664,"GB2-08":81.83360524090116},"per_game_all":{"GB2-01":39.57018270791675,"GB2-02":18.409259244154555,"GB2-03":45.950608996478785,"GB2-04":17.898016731341244,"GB2-05":51.73806445896892,"GB2-06":61.30515504478547,"GB2-07":47.80143142876231,"GB2-08":56.15572807301271},"per_game_match_totals_all":{"GB2-01":{"draws":325,"losses":290,"wins":193},"GB2-02":{"draws":565,"losses":111,"wins":90},"GB2-03":{"draws":292,"losses":265,"wins":255},"GB2-04":{"draws":522,"losses":165,"wins":107},"GB2-05":{"draws":0,"losses":384,"wins":404},"GB2-06":{"draws":73,"losses":305,"wins":478},"GB2-07":{"draws":0,"losses":413,"wins":413},"GB2-08":{"draws":206,"losses":192,"wins":476}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":104,"losses":102,"wins":114},"GB2-02":{"draws":159,"losses":27,"wins":48},"GB2-03":{"draws":102,"losses":41,"wins":91},"GB2-04":{"draws":136,"losses":56,"wins":50},"GB2-05":{"draws":0,"losses":95,"wins":143},"GB2-06":{"draws":25,"losses":44,"wins":183},"GB2-07":{"draws":0,"losses":109,"wins":147},"GB2-08":{"draws":2,"losses":25,"wins":239}},"medium":{"GB2-01":{"draws":110,"losses":86,"wins":46},"GB2-02":{"draws":204,"losses":43,"wins":11},"GB2-03":{"draws":146,"losses":100,"wins":65},"GB2-04":{"draws":166,"losses":52,"wins":20},"GB2-05":{"draws":0,"losses":155,"wins":171},"GB2-06":{"draws":25,"losses":150,"wins":123},"GB2-07":{"draws":0,"losses":158,"wins":124},"GB2-08":{"draws":200,"losses":112,"wins":32}},"none":{"GB2-01":{"draws":111,"losses":102,"wins":33},"GB2-02":{"draws":202,"losses":41,"wins":31},"GB2-03":{"draws":44,"losses":124,"wins":99},"GB2-04":{"draws":220,"losses":57,"wins":37},"GB2-05":{"draws":0,"losses":134,"wins":90},"GB2-06":{"draws":23,"losses":111,"wins":172},"GB2-07":{"draws":0,"losses":146,"wins":142},"GB2-08":{"draws":4,"losses":55,"wins":205}}},"per_game_raw_elo_all":{"GB2-01":1437.9608596315518,"GB2-02":1483.4887600669217,"GB2-03":1586.8922933796414,"GB2-04":1444.0752884699025,"GB2-05":1538.321148385845,"GB2-06":1676.0734523088397,"GB2-07":1510.797131050378,"GB2-08":1737.953813795388},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1520.1200824179782,"GB2-02":1489.068223724876,"GB2-03":1853.5765514492996,"GB2-04":1458.8734672756627,"GB2-05":1721.8939183081075,"GB2-06":2014.87542955774,"GB2-07":1682.1774714179971,"GB2-08":2077.0836541057433},"medium":{"GB2-01":1463.8453959707654,"GB2-02":1470.1239013621373,"GB2-03":1427.7987684691807,"GB2-04":1416.2823151197556,"GB2-05":1637.5421322613147,"GB2-06":1386.4439636276202,"GB2-07":1323.015355771146,"GB2-08":1345.9944426793504},"none":{"GB2-01":1329.9171005059115,"GB2-02":1491.2741551137517,"GB2-03":1479.3015602204446,"GB2-04":1457.07008301429,"GB2-05":1255.5273945881124,"GB2-06":1626.900963741159,"GB2-07":1527.1985659619909,"GB2-08":1790.7833446010702}},"per_game_tracks":{"highest":{"GB2-01":45.61493415632901,"GB2-02":19.044287744530894,"GB2-03":70.85712897377837,"GB2-04":19.985371794844777,"GB2-05":63.23579274922259,"GB2-06":81.68122776333043,"GB2-07":59.229693911875664,"GB2-08":81.83360524090116},"medium":{"GB2-01":41.34129805960164,"GB2-02":16.550806400289524,"GB2-03":31.16093776611165,"GB2-04":13.524183164803983,"GB2-05":58.16040418419862,"GB2-06":43.84626674582942,"GB2-07":35.2366026851926,"GB2-08":26.545702661167372},"none":{"GB2-01":31.754315907819613,"GB2-02":19.63268358764324,"GB2-03":35.833760249546316,"GB2-04":20.184495234374975,"GB2-05":33.81799644348555,"GB2-06":58.38797062519658,"GB2-07":48.937997689218676,"GB2-08":60.087876316969584}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":55.185255291851604,"medium":33.29577520839935,"none":38.579637006781816},"reasoning_agg":{"highest":{"max":81.83360524090116,"mean":55.185255291851604,"min":19.044287744530894},"medium":{"max":58.16040418419862,"mean":33.29577520839935,"min":13.524183164803983},"none":{"max":60.087876316969584,"mean":38.579637006781816,"min":19.63268358764324}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":81.83360524090116,"expected_score":41.37434635849482,"reasoning_variance":21.889480083452256,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.9792094771827706},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":81.83360524090116,"expected_score":49.933503861970856,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.251751429880748},"medium":{"ceiling_score":58.16040418419862,"expected_score":32.62033081341794,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.6754443949814117},"none":{"ceiling_score":60.087876316969584,"expected_score":41.56920440009566,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.989567393313841}}},{"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":42.909549379433756,"highest":56.87873766350323,"medium":37.91520962417879,"none":33.934700850619244},"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":"2026-09-25T14:17:09Z","match_totals_all":{"draws":5385,"losses":7533,"wins":8399},"match_totals_tracks":{"highest":{"draws":889,"losses":1969,"wins":3591},"medium":{"draws":1717,"losses":2719,"wins":2676},"none":{"draws":2779,"losses":2845,"wins":2132}},"model_slug":"stealth-ox-alpha","overall":{"max":67.13193639618068,"mean":42.271968576040024,"min":13.796926219903233},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":22,"overall_ranking_status":"ranked","per_game":{"GB2-01":49.54900667277811,"GB2-02":51.28648284773156,"GB2-03":57.64563528194297,"GB2-04":54.29144742349905,"GB2-05":58.54346412601527,"GB2-06":67.13193639618068,"GB2-07":59.59542381477149,"GB2-08":56.986504745106686},"per_game_all":{"GB2-01":48.33234435682943,"GB2-02":26.962752390890838,"GB2-03":44.27998155765965,"GB2-04":36.48809828736571,"GB2-05":52.96430585878604,"GB2-06":47.19456163319168,"GB2-07":46.56794115492681,"GB2-08":40.48640979581987},"per_game_match_totals_all":{"GB2-01":{"draws":401,"losses":876,"wins":1031},"GB2-02":{"draws":1325,"losses":254,"wins":377},"GB2-03":{"draws":1529,"losses":1537,"wins":1842},"GB2-04":{"draws":1151,"losses":454,"wins":716},"GB2-05":{"draws":0,"losses":1148,"wins":1258},"GB2-06":{"draws":146,"losses":1224,"wins":1060},"GB2-07":{"draws":0,"losses":1379,"wins":1329},"GB2-08":{"draws":833,"losses":661,"wins":786}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":51,"losses":359,"wins":384},"GB2-02":{"draws":175,"losses":43,"wins":278},"GB2-03":{"draws":209,"losses":252,"wins":606},"GB2-04":{"draws":235,"losses":91,"wins":376},"GB2-05":{"draws":0,"losses":345,"wins":443},"GB2-06":{"draws":93,"losses":276,"wins":501},"GB2-07":{"draws":0,"losses":348,"wins":548},"GB2-08":{"draws":126,"losses":255,"wins":455}},"medium":{"GB2-01":{"draws":122,"losses":179,"wins":333},"GB2-02":{"draws":549,"losses":98,"wins":75},"GB2-03":{"draws":332,"losses":669,"wins":813},"GB2-04":{"draws":399,"losses":166,"wins":197},"GB2-05":{"draws":0,"losses":412,"wins":378},"GB2-06":{"draws":28,"losses":421,"wins":171},"GB2-07":{"draws":0,"losses":471,"wins":387},"GB2-08":{"draws":287,"losses":303,"wins":322}},"none":{"GB2-01":{"draws":228,"losses":338,"wins":314},"GB2-02":{"draws":601,"losses":113,"wins":24},"GB2-03":{"draws":988,"losses":616,"wins":423},"GB2-04":{"draws":517,"losses":197,"wins":143},"GB2-05":{"draws":0,"losses":391,"wins":437},"GB2-06":{"draws":25,"losses":527,"wins":388},"GB2-07":{"draws":0,"losses":560,"wins":394},"GB2-08":{"draws":420,"losses":103,"wins":9}}},"per_game_raw_elo_all":{"GB2-01":1559.2647202621831,"GB2-02":1544.7716137654095,"GB2-03":1570.673676716734,"GB2-04":1567.5377088366768,"GB2-05":1557.473191123947,"GB2-06":1441.8383668815825,"GB2-07":1491.5060935628808,"GB2-08":1531.8750613261382},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1577.345424331282,"GB2-02":1717.3031610635599,"GB2-03":1714.6275748238265,"GB2-04":1686.5855614897616,"GB2-05":1646.2595980746028,"GB2-06":1772.4484196222327,"GB2-07":1685.8886855839849,"GB2-08":1749.339929690285},"medium":{"GB2-01":1650.141425370019,"GB2-02":1465.8008998324374,"GB2-03":1558.5361152807309,"GB2-04":1510.7841618976643,"GB2-05":1494.0060953819218,"GB2-06":1156.6289503283863,"GB2-07":1429.68078832153,"GB2-08":1526.4008661019027},"none":{"GB2-01":1450.3073110852486,"GB2-02":1451.2107804002305,"GB2-03":1438.8573400456446,"GB2-04":1505.243403122604,"GB2-05":1532.1538799153157,"GB2-06":1396.4377306941285,"GB2-07":1358.9488067831278,"GB2-08":1319.8843881862263}},"per_game_tracks":{"highest":{"GB2-01":49.54900667277811,"GB2-02":51.28648284773156,"GB2-03":57.64563528194297,"GB2-04":54.29144742349905,"GB2-05":58.54346412601527,"GB2-06":67.13193639618068,"GB2-07":59.59542381477149,"GB2-08":56.986504745106686},"medium":{"GB2-01":54.925489222319115,"GB2-02":15.804848105037715,"GB2-03":43.23380903288835,"GB2-04":27.904976519441306,"GB2-05":48.95613725220298,"GB2-06":29.979339503978853,"GB2-07":42.38360964767335,"GB2-08":40.13346770988864},"none":{"GB2-01":40.52253717539108,"GB2-02":13.796926219903233,"GB2-03":31.960500358147634,"GB2-04":27.26787091915678,"GB2-05":51.393316198139864,"GB2-06":44.47240899941553,"GB2-07":37.724790002335574,"GB2-08":24.339256932464274}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":56.87873766350324,"medium":36.582761420788586,"none":33.354406643828256},"reasoning_agg":{"highest":{"max":67.13193639618068,"mean":56.87873766350324,"min":49.54900667277811},"medium":{"max":54.925489222319115,"mean":36.582761420788586,"min":15.804848105037715},"none":{"max":51.393316198139864,"mean":33.354406643828256,"min":13.796926219903233}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":67.13193639618068,"expected_score":41.27860849201378,"reasoning_variance":23.52433101967498,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.9933600840262429},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":67.13193639618068,"expected_score":50.87693606346092,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.00180160004232},"medium":{"ceiling_score":54.925489222319115,"expected_score":37.59610294584087,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.013341525052283},"none":{"ceiling_score":51.393316198139864,"expected_score":35.36278646673955,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.0083798229112944}}},{"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":2.1645493884651272},"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":1.2313580991870414}},"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":0.5341545000000001},"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":2.164549388465127}},"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":4.9824165},"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":41.05207178752961,"highest":51.327641268902916,"medium":45.94264480977134,"none":25.885929283914564},"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":"2026-09-25T15:25:05Z","match_totals_all":{"draws":1970,"losses":2629,"wins":2586},"match_totals_tracks":{"highest":{"draws":471,"losses":694,"wins":1033},"medium":{"draws":567,"losses":693,"wins":833},"none":{"draws":932,"losses":1242,"wins":720}},"model_slug":"google-gemini-3-5-flash","overall":{"max":85.75732154194154,"mean":41.052071787529606,"min":5.490992930648422},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["fixed_coverage_incomplete"],"overall_official_rank":23,"overall_ranking_status":"partial","per_game":{"GB2-01":85.75732154194154,"GB2-02":28.850032552789482,"GB2-03":55.60089993691927,"GB2-04":15.041311096948304,"GB2-05":61.06832955325717,"GB2-06":69.73203415149305,"GB2-07":47.14767678741904,"GB2-08":47.423524530455495},"per_game_all":{"GB2-01":65.84641103411448,"GB2-02":15.718745434728158,"GB2-03":39.29603262970835,"GB2-04":21.740471556909615,"GB2-05":49.42752191661927,"GB2-06":61.12624544060847,"GB2-07":46.598701263220924,"GB2-08":28.662445024327592},"per_game_match_totals_all":{"GB2-01":{"draws":93,"losses":218,"wins":489},"GB2-02":{"draws":583,"losses":121,"wins":84},"GB2-03":{"draws":177,"losses":278,"wins":246},"GB2-04":{"draws":540,"losses":206,"wins":156},"GB2-05":{"draws":0,"losses":522,"wins":390},"GB2-06":{"draws":32,"losses":403,"wins":505},"GB2-07":{"draws":0,"losses":559,"wins":585},"GB2-08":{"draws":545,"losses":322,"wins":131}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":12,"losses":22,"wins":184},"GB2-02":{"draws":145,"losses":37,"wins":80},"GB2-03":{"draws":67,"losses":70,"wins":101},"GB2-04":{"draws":137,"losses":90,"wins":49},"GB2-05":{"draws":0,"losses":141,"wins":171},"GB2-06":{"draws":9,"losses":74,"wins":159},"GB2-07":{"draws":0,"losses":175,"wins":175},"GB2-08":{"draws":101,"losses":85,"wins":114}},"medium":{"GB2-01":{"draws":4,"losses":76,"wins":150},"GB2-02":{"draws":226,"losses":44,"wins":2},"GB2-03":{"draws":57,"losses":65,"wins":105},"GB2-04":{"draws":132,"losses":57,"wins":65},"GB2-05":{"draws":0,"losses":98,"wins":150},"GB2-06":{"draws":13,"losses":75,"wins":154},"GB2-07":{"draws":0,"losses":152,"wins":206},"GB2-08":{"draws":135,"losses":126,"wins":1}},"none":{"GB2-01":{"draws":77,"losses":120,"wins":155},"GB2-02":{"draws":212,"losses":40,"wins":2},"GB2-03":{"draws":53,"losses":143,"wins":40},"GB2-04":{"draws":271,"losses":59,"wins":42},"GB2-05":{"draws":0,"losses":283,"wins":69},"GB2-06":{"draws":10,"losses":254,"wins":192},"GB2-07":{"draws":0,"losses":232,"wins":204},"GB2-08":{"draws":309,"losses":111,"wins":16}}},"per_game_raw_elo_all":{"GB2-01":1808.2601641006988,"GB2-02":1464.0017627301306,"GB2-03":1517.8187612668207,"GB2-04":1471.0913539321227,"GB2-05":1503.25761456864,"GB2-06":1675.637267680878,"GB2-07":1492.0976710481075,"GB2-08":1377.3812140501516},"per_game_raw_elo_tracks":{"highest":{"GB2-01":2084.7316454501633,"GB2-02":1557.2698824483814,"GB2-03":1691.0453258781433,"GB2-04":1424.4930188095987,"GB2-05":1684.2097414809214,"GB2-06":1817.5502813354785,"GB2-07":1498.3071353060327,"GB2-08":1622.4769087588008},"medium":{"GB2-01":1816.8108855019566,"GB2-02":1442.9520788257767,"GB2-03":1601.1792080783332,"GB2-04":1560.0629310889913,"GB2-05":1776.5179187609167,"GB2-06":1834.450451701581,"GB2-07":1583.9642439877327,"GB2-08":1201.1802064230644},"none":{"GB2-01":1523.237961349977,"GB2-02":1391.7833269162336,"GB2-03":1261.2317498439854,"GB2-04":1428.7181118977787,"GB2-05":1049.0451834640826,"GB2-06":1374.911070005575,"GB2-07":1394.0216338505575,"GB2-08":1308.4865269685897}},"per_game_tracks":{"highest":{"GB2-01":85.75732154194154,"GB2-02":28.850032552789482,"GB2-03":55.60089993691927,"GB2-04":15.041311096948304,"GB2-05":61.06832955325717,"GB2-06":69.73203415149305,"GB2-07":47.14767678741904,"GB2-08":47.423524530455495},"medium":{"GB2-01":66.59984810877775,"GB2-02":12.815210820746566,"GB2-03":47.096115949915344,"GB2-04":35.351623972760336,"GB2-05":66.70860889776725,"GB2-06":70.75278873396961,"GB2-07":52.904620380720125,"GB2-08":15.312341613513716},"none":{"GB2-01":45.182063451624146,"GB2-02":5.490992930648422,"GB2-03":15.19108200229045,"GB2-04":14.82847960102021,"GB2-05":20.505627298833392,"GB2-06":42.893913436362745,"GB2-07":39.74380662152359,"GB2-08":23.25146892901356}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":51.327641268902916,"medium":45.94264480977134,"none":25.885929283914567},"reasoning_agg":{"highest":{"max":85.75732154194154,"mean":51.327641268902916,"min":15.041311096948304},"medium":{"max":70.75278873396961,"mean":45.94264480977134,"min":12.815210820746566},"none":{"max":45.182063451624146,"mean":25.885929283914567,"min":5.490992930648422}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":85.75732154194154,"expected_score":39.572802467821894,"reasoning_variance":25.44171198498835,"reliability_score":99.88853631741421,"uncertainty_avg":0.11146368258579398,"uncertainty_penalty":-1.4792693197077114},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":85.75732154194154,"expected_score":45.20986759823306,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.117773670669855},"medium":{"ceiling_score":70.75278873396961,"expected_score":47.668612199491335,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7259673897199974},"none":{"ceiling_score":45.182063451624146,"expected_score":25.839927605741295,"reliability_score":99.66560895224262,"uncertainty_avg":0.33439104775738193,"uncertainty_penalty":-0.04600167817327261}}},{"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":26.566350000000003},"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":43.16160461292457,"highest":56.835196114717284,"medium":38.67245608046029,"none":29.975112307677914},"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":"2026-09-25T15:10:59Z","match_totals_all":{"draws":1638,"losses":1185,"wins":1776},"match_totals_tracks":{"highest":{"draws":306,"losses":248,"wins":842},"medium":{"draws":608,"losses":494,"wins":632},"none":{"draws":724,"losses":443,"wins":302}},"model_slug":"gpt-5-5","overall":{"max":85.64043148326957,"mean":40.87754223283814,"min":10.026592849743277},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":24,"overall_ranking_status":"ranked","per_game":{"GB2-01":70.24122372942317,"GB2-03":36.09937739195498,"GB2-04":10.026592849743277,"GB2-05":66.56758096324789,"GB2-06":78.62474263949787,"GB2-07":85.64043148326957,"GB2-08":50.64642374588417},"per_game_all":{"GB2-01":53.11033104726388,"GB2-03":27.538310993580737,"GB2-04":14.853193802801735,"GB2-05":62.775527352093654,"GB2-07":62.91706204032068,"GB2-08":37.775202441486734},"per_game_match_totals_all":{"GB2-01":{"draws":339,"losses":63,"wins":162},"GB2-02":{"draws":345,"losses":48,"wins":49},"GB2-03":{"draws":175,"losses":166,"wins":119},"GB2-04":{"draws":414,"losses":162,"wins":77},"GB2-05":{"draws":0,"losses":165,"wins":363},"GB2-06":{"draws":6,"losses":209,"wins":251},"GB2-07":{"draws":0,"losses":226,"wins":496},"GB2-08":{"draws":359,"losses":146,"wins":259}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":54,"losses":23,"wins":85},"GB2-03":{"draws":50,"losses":50,"wins":56},"GB2-04":{"draws":129,"losses":65,"wins":20},"GB2-05":{"draws":0,"losses":36,"wins":148},"GB2-06":{"draws":4,"losses":22,"wins":162},"GB2-07":{"draws":0,"losses":23,"wins":211},"GB2-08":{"draws":69,"losses":29,"wins":160}},"medium":{"GB2-01":{"draws":130,"losses":6,"wins":60},"GB2-02":{"draws":142,"losses":27,"wins":49},"GB2-03":{"draws":64,"losses":59,"wins":27},"GB2-04":{"draws":149,"losses":49,"wins":32},"GB2-05":{"draws":0,"losses":45,"wins":123},"GB2-06":{"draws":2,"losses":187,"wins":89},"GB2-07":{"draws":0,"losses":69,"wins":163},"GB2-08":{"draws":121,"losses":52,"wins":89}},"none":{"GB2-01":{"draws":155,"losses":34,"wins":17},"GB2-02":{"draws":203,"losses":21,"wins":0},"GB2-03":{"draws":61,"losses":57,"wins":36},"GB2-04":{"draws":136,"losses":48,"wins":25},"GB2-05":{"draws":0,"losses":84,"wins":92},"GB2-07":{"draws":0,"losses":134,"wins":122},"GB2-08":{"draws":169,"losses":65,"wins":10}}},"per_game_raw_elo_all":{"GB2-01":1631.5507914406844,"GB2-03":1398.8131427757028,"GB2-04":1426.2799034816926,"GB2-05":1718.7921995340257,"GB2-07":1737.9932128386688,"GB2-08":1497.3773002549935},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1872.6133126290345,"GB2-03":1489.6170637154105,"GB2-04":1394.516912386562,"GB2-05":1778.3379873195004,"GB2-06":1968.2185266674333,"GB2-07":2077.3800463802863,"GB2-08":1666.72185236652},"medium":{"GB2-01":1597.6577112125444,"GB2-02":1491.1983241231044,"GB2-03":1292.4651870198682,"GB2-04":1468.6023650157663,"GB2-05":1877.3036719014776,"GB2-06":1150.2999734403245,"GB2-07":1696.2581746078608,"GB2-08":1503.0648943012557},"none":{"GB2-01":1424.3813504804746,"GB2-02":1445.100021197292,"GB2-03":1414.3571775918304,"GB2-04":1415.7204330427496,"GB2-05":1500.7349393810994,"GB2-07":1440.3414175278592,"GB2-08":1322.3451540972053}},"per_game_tracks":{"highest":{"GB2-01":70.24122372942317,"GB2-03":36.09937739195498,"GB2-04":10.026592849743277,"GB2-05":66.56758096324789,"GB2-06":78.62474263949787,"GB2-07":85.64043148326957,"GB2-08":50.64642374588417},"medium":{"GB2-01":50.73139480630345,"GB2-02":19.212396895406123,"GB2-03":17.509396641546054,"GB2-04":21.354567805952815,"GB2-05":72.713931668433,"GB2-06":29.53417748662991,"GB2-07":60.08939481420384,"GB2-08":38.23438852520712},"none":{"GB2-01":38.358374606065006,"GB2-02":12.771607546272488,"GB2-03":29.006158947241175,"GB2-04":13.178420752709116,"GB2-05":49.045069424600065,"GB2-07":43.021359823488645,"GB2-08":24.444795053368917}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.969194898876594,"medium":38.67245608046029,"none":28.990975719177527},"reasoning_agg":{"highest":{"max":85.64043148326957,"mean":54.969194898876594,"min":10.026592849743277},"medium":{"max":72.713931668433,"mean":38.67245608046029,"min":17.509396641546054},"none":{"max":49.045069424600065,"mean":28.990975719177527,"min":12.771607546272488}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":85.64043148326957,"expected_score":41.93214163078219,"reasoning_variance":25.978219179699067,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.0545993979440524},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":85.64043148326957,"expected_score":51.024882507358676,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.9443123915179186},"medium":{"ceiling_score":72.713931668433,"expected_score":37.912971958971056,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7594841214892369},"none":{"ceiling_score":49.045069424600065,"expected_score":31.497872489969957,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.50689677079243}}},{"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":0.21156558},"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":40.83778621244848,"highest":50.42811883048915,"medium":36.5572086512823,"none":35.528031155574},"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":"2026-09-25T14:21:47Z","match_totals_all":{"draws":526,"losses":752,"wins":851},"match_totals_tracks":{"highest":{"draws":148,"losses":197,"wins":378},"medium":{"draws":175,"losses":267,"wins":248},"none":{"draws":203,"losses":288,"wins":225}},"model_slug":"z-ai-glm-5-3-flashx","overall":{"max":71.74427757233467,"mean":40.837786212448485,"min":7.080049745365206},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":25,"overall_ranking_status":"ranked","per_game":{"GB2-01":36.075433997538745,"GB2-02":35.13947827988383,"GB2-03":52.44037344594306,"GB2-04":56.03914060818941,"GB2-05":58.763634521125965,"GB2-06":71.74427757233467,"GB2-07":68.6758710523356,"GB2-08":24.546741166561926},"per_game_all":{"GB2-01":48.155537345561605,"GB2-02":21.09485324992194,"GB2-03":38.36891203420237,"GB2-04":35.251838482268745,"GB2-05":48.21934145292564,"GB2-06":59.85056746744755,"GB2-07":58.51518441002983,"GB2-08":17.2460552572302},"per_game_match_totals_all":{"GB2-01":{"draws":20,"losses":84,"wins":138},"GB2-02":{"draws":204,"losses":45,"wins":55},"GB2-03":{"draws":25,"losses":78,"wins":83},"GB2-04":{"draws":134,"losses":36,"wins":81},"GB2-05":{"draws":0,"losses":145,"wins":119},"GB2-06":{"draws":12,"losses":106,"wins":164},"GB2-07":{"draws":0,"losses":98,"wins":192},"GB2-08":{"draws":131,"losses":160,"wins":19}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":50,"wins":34},"GB2-02":{"draws":53,"losses":11,"wins":38},"GB2-03":{"draws":1,"losses":15,"wins":46},"GB2-04":{"draws":30,"losses":6,"wins":49},"GB2-05":{"draws":0,"losses":29,"wins":51},"GB2-06":{"draws":5,"losses":19,"wins":78},"GB2-07":{"draws":0,"losses":25,"wins":69},"GB2-08":{"draws":59,"losses":42,"wins":13}},"medium":{"GB2-01":{"draws":3,"losses":13,"wins":64},"GB2-02":{"draws":74,"losses":8,"wins":16},"GB2-03":{"draws":10,"losses":31,"wins":23},"GB2-04":{"draws":51,"losses":14,"wins":21},"GB2-05":{"draws":0,"losses":64,"wins":26},"GB2-06":{"draws":3,"losses":40,"wins":41},"GB2-07":{"draws":0,"losses":38,"wins":56},"GB2-08":{"draws":34,"losses":59,"wins":1}},"none":{"GB2-01":{"draws":17,"losses":21,"wins":40},"GB2-02":{"draws":77,"losses":26,"wins":1},"GB2-03":{"draws":14,"losses":32,"wins":14},"GB2-04":{"draws":53,"losses":16,"wins":11},"GB2-05":{"draws":0,"losses":52,"wins":42},"GB2-06":{"draws":4,"losses":47,"wins":45},"GB2-07":{"draws":0,"losses":35,"wins":67},"GB2-08":{"draws":38,"losses":59,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1577.5087286110436,"GB2-02":1517.086213642987,"GB2-03":1532.2472755207898,"GB2-04":1577.840238229388,"GB2-05":1500.0280624694742,"GB2-06":1669.425013155218,"GB2-07":1687.0624817720047,"GB2-08":1241.233103188564},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1408.1229581263374,"GB2-02":1616.6787937426257,"GB2-03":1681.9417056415027,"GB2-04":1715.2006324965307,"GB2-05":1669.4459210255652,"GB2-06":1864.6192415868886,"GB2-07":1839.206746931014,"GB2-08":1335.4329200529928},"medium":{"GB2-01":1795.020483743773,"GB2-02":1511.5919741849273,"GB2-03":1504.789130216092,"GB2-04":1535.8372344019856,"GB2-05":1316.9295466118283,"GB2-06":1510.5273787833557,"GB2-07":1556.1370577997548,"GB2-08":1109.1345222853001},"none":{"GB2-01":1529.3827439630202,"GB2-02":1422.9878730014084,"GB2-03":1410.0109907047743,"GB2-04":1482.482847789648,"GB2-05":1513.7087197710289,"GB2-06":1633.1284190954095,"GB2-07":1665.843640585245,"GB2-08":1279.1318672273992}},"per_game_tracks":{"highest":{"GB2-01":36.075433997538745,"GB2-02":35.13947827988383,"GB2-03":52.44037344594306,"GB2-04":56.03914060818941,"GB2-05":58.763634521125965,"GB2-06":71.74427757233467,"GB2-07":68.6758710523356,"GB2-08":24.546741166561926},"medium":{"GB2-01":63.73802956993577,"GB2-02":20.229397698507874,"GB2-03":35.86266928865096,"GB2-04":29.002702443895366,"GB2-05":36.723346411404776,"GB2-06":50.11749746309352,"GB2-07":49.703976589404945,"GB2-08":7.080049745365206},"none":{"GB2-01":44.65314846921031,"GB2-02":7.915683771374111,"GB2-03":26.803693368013082,"GB2-04":20.713672394721467,"GB2-05":49.17104342624617,"GB2-06":57.68992736691443,"GB2-07":57.16570558834896,"GB2-08":20.111374859763473}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":50.42811883048915,"medium":36.5572086512823,"none":35.528031155574},"reasoning_agg":{"highest":{"max":71.74427757233467,"mean":50.42811883048915,"min":24.546741166561926},"medium":{"max":63.73802956993577,"mean":36.5572086512823,"min":7.080049745365206},"none":{"max":57.68992736691443,"mean":35.528031155574,"min":7.915683771374111}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":71.74427757233467,"expected_score":40.62111400900426,"reasoning_variance":14.900087674915149,"reliability_score":90.45610829054593,"uncertainty_avg":9.543891709454067,"uncertainty_penalty":-0.21667220344422589},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":71.74427757233467,"expected_score":44.915158834696776,"reliability_score":90.85553484006091,"uncertainty_avg":9.14446515993909,"uncertainty_penalty":-5.512959995792372},"medium":{"ceiling_score":63.73802956993577,"expected_score":38.164494627132605,"reliability_score":89.91560851821431,"uncertainty_avg":10.084391481785687,"uncertainty_penalty":1.6072859758503029},"none":{"ceiling_score":57.68992736691443,"expected_score":38.78368856518339,"reliability_score":90.59718151336257,"uncertainty_avg":9.402818486637424,"uncertainty_penalty":3.255657409609391}}},{"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":0.14258062},"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":0.0234374}},"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":0.14258062000000002},"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":0.0234374}},"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":0.16601801999999996},"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":47.115778688864275,"none":35.62005544829645},"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":"2026-09-25T12:06:40Z","match_totals_all":{"draws":300,"losses":504,"wins":520},"match_totals_tracks":{"medium":{"draws":126,"losses":212,"wins":350},"none":{"draws":174,"losses":292,"wins":170}},"model_slug":"xiaomi-mimo-v2-6-flash","overall":{"max":73.64786897600108,"mean":40.78318198083055,"min":11.524793275000588},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","missing_or_non_distinct_settings","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":26,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":16,"losses":51,"wins":87},"GB2-02":{"draws":122,"losses":35,"wins":43},"GB2-03":{"draws":16,"losses":60,"wins":48},"GB2-04":{"draws":13,"losses":21,"wins":42},"GB2-05":{"draws":0,"losses":86,"wins":92},"GB2-06":{"draws":14,"losses":75,"wins":99},"GB2-07":{"draws":0,"losses":79,"wins":107},"GB2-08":{"draws":119,"losses":97,"wins":2}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":2,"losses":32,"wins":44},"GB2-02":{"draws":38,"losses":12,"wins":42},"GB2-03":{"draws":3,"losses":25,"wins":34},"GB2-04":{"draws":13,"losses":21,"wins":42},"GB2-05":{"draws":0,"losses":38,"wins":52},"GB2-06":{"draws":7,"losses":32,"wins":59},"GB2-07":{"draws":0,"losses":11,"wins":75},"GB2-08":{"draws":63,"losses":41,"wins":2}},"none":{"GB2-01":{"draws":14,"losses":19,"wins":43},"GB2-02":{"draws":84,"losses":23,"wins":1},"GB2-03":{"draws":13,"losses":35,"wins":14},"GB2-05":{"draws":0,"losses":48,"wins":40},"GB2-06":{"draws":7,"losses":43,"wins":40},"GB2-07":{"draws":0,"losses":68,"wins":32},"GB2-08":{"draws":56,"losses":56,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1559.4873648676273,"GB2-02":1629.2719135698069,"GB2-03":1537.8354628199563,"GB2-04":1653.517725810686,"GB2-05":1612.6238144120402,"GB2-06":1653.5720186416438,"GB2-07":1915.2366881308399,"GB2-08":1280.841049518355},"none":{"GB2-01":1664.6087584065551,"GB2-02":1447.8928882780958,"GB2-03":1407.5447175645834,"GB2-05":1547.4622565590478,"GB2-06":1558.6492842445664,"GB2-07":1356.4235677106053,"GB2-08":1224.9878973868924}},"per_game_tracks":{"medium":{"GB2-01":46.81148803602438,"GB2-02":36.622136291619164,"GB2-03":38.89535829138528,"GB2-04":46.35844545212433,"GB2-05":55.34370347170291,"GB2-06":58.94960636853664,"GB2-07":73.64786897600108,"GB2-08":20.29762262352045},"none":{"GB2-01":54.30649302297495,"GB2-02":11.524793275000588,"GB2-03":26.648906753764663,"GB2-05":51.210868821751404,"GB2-06":53.11187823957251,"GB2-07":36.40173017070555,"GB2-08":16.135717854305447}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":47.115778688864275,"none":34.45058527279682},"reasoning_agg":{"medium":{"max":73.64786897600108,"mean":47.115778688864275,"min":20.29762262352045},"none":{"max":54.30649302297495,"mean":34.45058527279682,"min":11.524793275000588}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":73.64786897600108,"reasoning_variance":12.665193416067453},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":73.64786897600108,"expected_score":50.677112862059765,"reliability_score":89.66438366990724,"uncertainty_avg":10.335616330092758,"uncertainty_penalty":3.5613341731954904},"none":{"ceiling_score":54.30649302297495,"expected_score":39.238486649519885,"reliability_score":90.88318284402271,"uncertainty_avg":9.116817155977285,"uncertainty_penalty":4.787901376723063}}},{"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":0.969774}},"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":0.969774},"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":4.481648},"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":40.291837618080805,"highest":54.36706229997475,"medium":33.83694392650825,"none":34.088585523137525},"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":"2026-09-25T14:19:18Z","match_totals_all":{"draws":569,"losses":586,"wins":780},"match_totals_tracks":{"highest":{"draws":148,"losses":74,"wins":352},"medium":{"draws":193,"losses":278,"wins":220},"none":{"draws":228,"losses":234,"wins":208}},"model_slug":"qwen-qwen3-8-max-0902","overall":{"max":76.38881018245638,"mean":40.764197249873504,"min":2.3421974844057343},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":27,"overall_ranking_status":"partial","per_game":{"GB2-01":50.78300254547936,"GB2-02":31.282600931503342,"GB2-03":47.941446429504964,"GB2-04":63.02862383954646,"GB2-05":76.38881018245638,"GB2-06":72.87471300160755,"GB2-08":38.27023916972515},"per_game_all":{"GB2-01":36.250833224430984,"GB2-02":19.88619841184828,"GB2-03":41.20303420876328,"GB2-04":27.31558262751206,"GB2-05":59.658391116626866,"GB2-06":66.31926885325451,"GB2-08":31.40955488412965},"per_game_match_totals_all":{"GB2-01":{"draws":65,"losses":90,"wins":59},"GB2-02":{"draws":204,"losses":42,"wins":42},"GB2-03":{"draws":21,"losses":60,"wins":105},"GB2-04":{"draws":109,"losses":56,"wins":72},"GB2-05":{"draws":0,"losses":81,"wins":161},"GB2-06":{"draws":19,"losses":62,"wins":201},"GB2-07":{"draws":0,"losses":108,"wins":76},"GB2-08":{"draws":151,"losses":87,"wins":64}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":25,"losses":12,"wins":33},"GB2-02":{"draws":59,"losses":9,"wins":26},"GB2-03":{"draws":3,"losses":15,"wins":50},"GB2-04":{"draws":9,"losses":6,"wins":59},"GB2-05":{"draws":0,"losses":5,"wins":69},"GB2-06":{"draws":8,"losses":6,"wins":76},"GB2-08":{"draws":44,"losses":21,"wins":39}},"medium":{"GB2-01":{"draws":14,"losses":50,"wins":18},"GB2-02":{"draws":69,"losses":15,"wins":12},"GB2-03":{"draws":9,"losses":23,"wins":32},"GB2-04":{"draws":53,"losses":17,"wins":11},"GB2-05":{"draws":0,"losses":50,"wins":36},"GB2-06":{"draws":4,"losses":41,"wins":47},"GB2-07":{"draws":0,"losses":46,"wins":44},"GB2-08":{"draws":44,"losses":36,"wins":20}},"none":{"GB2-01":{"draws":26,"losses":28,"wins":8},"GB2-02":{"draws":76,"losses":18,"wins":4},"GB2-03":{"draws":9,"losses":22,"wins":23},"GB2-04":{"draws":47,"losses":33,"wins":2},"GB2-05":{"draws":0,"losses":26,"wins":56},"GB2-06":{"draws":7,"losses":15,"wins":78},"GB2-07":{"draws":0,"losses":62,"wins":32},"GB2-08":{"draws":63,"losses":30,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1414.4407542873178,"GB2-02":1509.5715982835634,"GB2-03":1562.5597793532881,"GB2-04":1526.5311101762334,"GB2-05":1683.536431005645,"GB2-06":1776.4569794557676,"GB2-08":1428.196050310575},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1617.3499846972302,"GB2-02":1590.9174124025324,"GB2-03":1631.8364247304644,"GB2-04":1764.5604542591154,"GB2-05":1951.080125087102,"GB2-06":1885.8535702985014,"GB2-08":1517.9079956486037},"medium":{"GB2-01":1271.4328293956996,"GB2-02":1490.4873472445463,"GB2-03":1565.8608992836625,"GB2-04":1454.798694413226,"GB2-05":1421.8335327503344,"GB2-06":1578.059466017882,"GB2-07":1450.8170161899664,"GB2-08":1395.4357551604487},"none":{"GB2-01":1354.539448769024,"GB2-02":1447.3100352036117,"GB2-03":1489.9820140457375,"GB2-04":1360.2341818563582,"GB2-05":1677.695635179499,"GB2-06":1865.4579020509198,"GB2-07":1340.6210604790344,"GB2-08":1371.2444001226727}},"per_game_tracks":{"highest":{"GB2-01":50.78300254547936,"GB2-02":31.282600931503342,"GB2-03":47.941446429504964,"GB2-04":63.02862383954646,"GB2-05":76.38881018245638,"GB2-06":72.87471300160755,"GB2-08":38.27023916972515},"medium":{"GB2-01":26.238232783733412,"GB2-02":17.199228787720973,"GB2-03":41.60300379005268,"GB2-04":16.575926558583998,"GB2-05":43.26930512569967,"GB2-06":54.31161562786239,"GB2-07":42.58541659334441,"GB2-08":28.912822145068468},"none":{"GB2-01":31.73126434408019,"GB2-02":11.176765516320527,"GB2-03":34.06465240673219,"GB2-04":2.3421974844057343,"GB2-05":59.317058041724536,"GB2-06":71.7714779302936,"GB2-07":35.25966512394811,"GB2-08":27.045603337595335}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":54.36706229997475,"medium":33.83694392650825,"none":34.088585523137525},"reasoning_agg":{"highest":{"max":76.38881018245638,"mean":54.36706229997475,"min":31.282600931503342},"medium":{"max":54.31161562786239,"mean":33.83694392650825,"min":16.575926558583998},"none":{"max":71.7714779302936,"mean":34.088585523137525,"min":2.3421974844057343}},"reasoning_labels":{"highest":"Xhigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":76.38881018245638,"expected_score":40.764507823729865,"reasoning_variance":20.5301183734665,"reliability_score":88.7008651400927,"uncertainty_avg":11.299134859907296,"uncertainty_penalty":0.0003105738563604632},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.38881018245638,"expected_score":49.746238393201985,"reliability_score":88.3913962316739,"uncertainty_avg":11.6086037683261,"uncertainty_penalty":-4.620823906772763},"medium":{"ceiling_score":54.31161562786239,"expected_score":35.995058753731726,"reliability_score":89.93726482393001,"uncertainty_avg":10.06273517607,"uncertainty_penalty":2.1581148272234785},"none":{"ceiling_score":71.7714779302936,"expected_score":37.85738955237648,"reliability_score":88.53338953605449,"uncertainty_avg":11.466610463945516,"uncertainty_penalty":3.7688040292389573}}},{"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":0.6080262},"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":4.208936999999999}},"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":7.1402928},"codegen_latency_ms":{"attempt_count":40,"max_ms":1201344,"mean_ms":515468.5833333333,"min_ms":64944,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":15,"max_ms":1201344,"mean_ms":973286.5,"min_ms":605299,"run_count":8},"medium":{"attempt_count":16,"max_ms":754602,"mean_ms":479215.25,"min_ms":119309,"run_count":8},"none":{"attempt_count":9,"max_ms":115016,"mean_ms":93904.0,"min_ms":64944,"run_count":8}},"codegen_output_tokens":{"attempt_count":40,"output_max":40000,"output_mean":17970.666666666668,"output_min":2237,"run_count":24},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":15,"output_max":40000,"output_mean":33312.25,"output_min":20000,"run_count":8},"medium":{"attempt_count":16,"output_max":27465,"output_mean":17219.125,"output_min":4345,"run_count":8},"none":{"attempt_count":9,"output_max":4534,"output_mean":3380.625,"output_min":2237,"run_count":8}},"display_name":"Kimi K3","economics":{"all":35.49712921670735,"highest":43.19539960693221,"medium":38.00861893086849,"none":42.71441221564036},"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":"2026-09-25T14:33:19Z","match_totals_all":{"draws":2741,"losses":2867,"wins":3248},"match_totals_tracks":{"highest":{"draws":637,"losses":555,"wins":782},"medium":{"draws":1162,"losses":1162,"wins":1052},"none":{"draws":942,"losses":1150,"wins":1414}},"model_slug":"moonshotai-kimi-k3","overall":{"max":88.12366220504157,"mean":40.144514399459716,"min":10.856245227633352},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":28,"overall_ranking_status":"partial","per_game":{"GB2-01":58.56757191941488,"GB2-02":10.856245227633352,"GB2-03":37.017147044794186,"GB2-04":54.50674408464692,"GB2-07":55.029289758171764},"per_game_all":{"GB2-01":52.52459582831261,"GB2-02":13.521714755658914,"GB2-03":38.84820705318693,"GB2-04":33.39322465264262,"GB2-07":39.19790379373566},"per_game_match_totals_all":{"GB2-01":{"draws":395,"losses":367,"wins":485},"GB2-02":{"draws":886,"losses":144,"wins":36},"GB2-03":{"draws":392,"losses":336,"wins":403},"GB2-04":{"draws":605,"losses":252,"wins":352},"GB2-05":{"draws":0,"losses":412,"wins":555},"GB2-06":{"draws":87,"losses":434,"wins":459},"GB2-07":{"draws":0,"losses":754,"wins":536},"GB2-08":{"draws":376,"losses":168,"wins":422}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":42,"losses":127,"wins":223},"GB2-02":{"draws":302,"losses":53,"wins":13},"GB2-03":{"draws":184,"losses":116,"wins":90},"GB2-04":{"draws":109,"losses":62,"wins":191},"GB2-07":{"draws":0,"losses":197,"wins":265}},"medium":{"GB2-01":{"draws":59,"losses":123,"wins":170},"GB2-02":{"draws":275,"losses":41,"wins":10},"GB2-03":{"draws":104,"losses":79,"wins":154},"GB2-04":{"draws":305,"losses":71,"wins":59},"GB2-05":{"draws":0,"losses":213,"wins":261},"GB2-06":{"draws":43,"losses":204,"wins":245},"GB2-07":{"draws":0,"losses":287,"wins":125},"GB2-08":{"draws":376,"losses":144,"wins":28}},"none":{"GB2-01":{"draws":294,"losses":117,"wins":92},"GB2-02":{"draws":309,"losses":50,"wins":13},"GB2-03":{"draws":104,"losses":141,"wins":159},"GB2-04":{"draws":191,"losses":119,"wins":102},"GB2-05":{"draws":0,"losses":199,"wins":294},"GB2-06":{"draws":44,"losses":230,"wins":214},"GB2-07":{"draws":0,"losses":270,"wins":146},"GB2-08":{"draws":0,"losses":24,"wins":394}}},"per_game_raw_elo_all":{"GB2-01":1613.9320756208626,"GB2-02":1444.9779439313616,"GB2-03":1507.5592751933636,"GB2-04":1541.9842788283065,"GB2-07":1377.6291118630916},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1698.6355858236166,"GB2-02":1425.6557046760618,"GB2-03":1487.6866651776409,"GB2-04":1682.9100428921965,"GB2-07":1613.1437056065654},"medium":{"GB2-01":1742.1375362854433,"GB2-02":1440.9628140050902,"GB2-03":1597.251265689971,"GB2-04":1433.9772585746641,"GB2-05":1560.9996058964011,"GB2-06":1563.7774959551684,"GB2-07":1243.0906169640273,"GB2-08":1342.9574897840018},"none":{"GB2-01":1401.0231047535278,"GB2-02":1468.3153131129332,"GB2-03":1437.7398947124789,"GB2-04":1509.0655350180587,"GB2-05":1650.0349636228016,"GB2-06":1431.5641181916208,"GB2-07":1276.6530130186823,"GB2-08":2154.9857455992246}},"per_game_tracks":{"highest":{"GB2-01":58.56757191941488,"GB2-02":10.856245227633352,"GB2-03":37.017147044794186,"GB2-04":54.50674408464692,"GB2-07":55.029289758171764},"medium":{"GB2-01":61.60666625896725,"GB2-02":12.829263374876211,"GB2-03":47.17183438241479,"GB2-04":17.209086808065273,"GB2-05":53.57759582487964,"GB2-06":54.86613972193045,"GB2-07":30.15433037896266,"GB2-08":26.65403469685162},"none":{"GB2-01":37.39954930655572,"GB2-02":16.87963566446718,"GB2-03":32.35563973235182,"GB2-04":28.46384306521568,"GB2-05":59.20674314072263,"GB2-06":46.87613336669571,"GB2-07":32.41009124407256,"GB2-08":88.12366220504157}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":39.710512051870296,"medium":38.00861893086849,"none":42.71441221564036},"reasoning_agg":{"highest":{"max":58.56757191941488,"mean":39.710512051870296,"min":10.856245227633352},"medium":{"max":61.60666625896725,"mean":38.00861893086849,"min":12.829263374876211},"none":{"max":88.12366220504157,"mean":42.71441221564036,"min":16.87963566446718}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Low"},"reasoning_settings":{"balanced":"high","baseline":"low","intensive":"max"},"score_diagnostics":{"ceiling_score":88.12366220504157,"expected_score":34.187890893801196,"reasoning_variance":4.705793284771872,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-5.95662350565852},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":58.56757191941488,"expected_score":36.934240466470825,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.7762715853994706},"medium":{"ceiling_score":61.60666625896725,"expected_score":38.15799735355662,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.14937842268813029},"none":{"ceiling_score":88.12366220504157,"expected_score":46.05083626178848,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.3364240461481245}}},{"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":0.376168},"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":0.376168},"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":0.19141049999999998},"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":0.8154702500000001},"codegen_latency_ms":{"attempt_count":20,"max_ms":328036,"mean_ms":53436.555555555555,"min_ms":14709,"run_count":18},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":2,"max_ms":328036,"mean_ms":222798.5,"min_ms":117561,"run_count":2},"medium":{"attempt_count":9,"max_ms":66794,"mean_ms":45688.625,"min_ms":28293,"run_count":8},"none":{"attempt_count":9,"max_ms":26924,"mean_ms":18844.0,"min_ms":14709,"run_count":8}},"codegen_output_tokens":{"attempt_count":20,"output_max":31468,"output_mean":8149.833333333333,"output_min":2554,"run_count":18},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":2,"output_max":31468,"output_mean":26858.0,"output_min":22248,"run_count":2},"medium":{"attempt_count":9,"output_max":11293,"output_mean":8521.75,"output_min":5500,"run_count":8},"none":{"attempt_count":9,"output_max":3991,"output_mean":3100.875,"output_min":2554,"run_count":8}},"display_name":"Muse Spark 1.2","economics":{"all":44.626631667604926,"highest":46.151515774593946,"medium":42.15120052283497,"none":32.31949261917336},"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":"2026-09-25T14:22:13Z","match_totals_all":{"draws":1413,"losses":2390,"wins":2413},"match_totals_tracks":{"highest":{"draws":96,"losses":306,"wins":370},"medium":{"draws":621,"losses":789,"wins":1120},"none":{"draws":696,"losses":1295,"wins":923}},"model_slug":"meta-muse-spark-1-2","overall":{"max":72.07963331402082,"mean":39.74610318614332,"min":8.986553392204476},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":29,"overall_ranking_status":"partial","per_game":{"GB2-01":52.012365091494885,"GB2-03":40.290666457693014},"per_game_all":{"GB2-01":53.779221133229505,"GB2-03":35.474042201980346},"per_game_match_totals_all":{"GB2-01":{"draws":188,"losses":328,"wins":520},"GB2-02":{"draws":483,"losses":115,"wins":33},"GB2-03":{"draws":235,"losses":466,"wins":460},"GB2-04":{"draws":430,"losses":136,"wins":106},"GB2-05":{"draws":0,"losses":401,"wins":423},"GB2-06":{"draws":3,"losses":279,"wins":78},"GB2-07":{"draws":0,"losses":381,"wins":373},"GB2-08":{"draws":74,"losses":284,"wins":420}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":36,"losses":146,"wins":198},"GB2-03":{"draws":60,"losses":160,"wins":172}},"medium":{"GB2-01":{"draws":11,"losses":61,"wins":250},"GB2-02":{"draws":252,"losses":57,"wins":26},"GB2-03":{"draws":115,"losses":137,"wins":127},"GB2-04":{"draws":178,"losses":77,"wins":55},"GB2-05":{"draws":0,"losses":206,"wins":208},"GB2-07":{"draws":0,"losses":146,"wins":228},"GB2-08":{"draws":65,"losses":105,"wins":226}},"none":{"GB2-01":{"draws":141,"losses":121,"wins":72},"GB2-02":{"draws":231,"losses":58,"wins":7},"GB2-03":{"draws":60,"losses":169,"wins":161},"GB2-04":{"draws":252,"losses":59,"wins":51},"GB2-05":{"draws":0,"losses":195,"wins":215},"GB2-06":{"draws":3,"losses":279,"wins":78},"GB2-07":{"draws":0,"losses":235,"wins":145},"GB2-08":{"draws":9,"losses":179,"wins":194}}},"per_game_raw_elo_all":{"GB2-01":1633.2046318334044,"GB2-03":1471.3491982327596},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1607.5185452601124,"GB2-03":1522.4622993750897},"medium":{"GB2-01":1889.1817125892937,"GB2-02":1446.0048383762835,"GB2-03":1453.0058603990226,"GB2-04":1417.5004246962953,"GB2-05":1503.9507083566857,"GB2-07":1675.240369774397,"GB2-08":1686.6240042460931},"none":{"GB2-01":1402.9136376508068,"GB2-02":1414.7663744997578,"GB2-03":1438.579434924167,"GB2-04":1443.5382030918151,"GB2-05":1607.431668197681,"GB2-06":1049.1009470500528,"GB2-07":1320.3770693573304,"GB2-08":1604.4853319623594}},"per_game_tracks":{"highest":{"GB2-01":52.012365091494885,"GB2-03":40.290666457693014},"medium":{"GB2-01":72.07963331402082,"GB2-02":13.581319779736006,"GB2-03":33.73006163008332,"GB2-04":14.189855510586924,"GB2-05":49.90440468938342,"GB2-07":59.05264202522787,"GB2-08":52.520486710806374},"none":{"GB2-01":37.24566499417282,"GB2-02":8.986553392204476,"GB2-03":32.401398518164704,"GB2-04":18.374820319063318,"GB2-05":56.41476958488925,"GB2-06":23.59669007853958,"GB2-07":35.279940763003445,"GB2-08":46.256103303349285}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":46.151515774593946,"medium":40.76730116466266,"none":32.31949261917336},"reasoning_agg":{"highest":{"max":52.012365091494885,"mean":46.151515774593946,"min":40.290666457693014},"medium":{"max":72.07963331402082,"mean":40.76730116466266,"min":13.581319779736006},"none":{"max":56.41476958488925,"mean":32.31949261917336,"min":8.986553392204476}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":72.07963331402082,"expected_score":42.26322781229493,"reasoning_variance":13.832023155420586,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.517124626151606},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":52.012365091494885,"expected_score":37.531486977071644,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.620028797522302},"medium":{"ceiling_score":72.07963331402082,"expected_score":43.01710802720317,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.2498068625405097},"none":{"ceiling_score":56.41476958488925,"expected_score":32.67124372638089,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.35175110720752656}}},{"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":0.15272934},"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":0.392731284},"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":39.5737668556252,"highest":53.001670581745614,"medium":40.942459007178655,"none":24.77717097795133},"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":"2026-09-25T15:54:23Z","match_totals_all":{"draws":592,"losses":638,"wins":808},"match_totals_tracks":{"highest":{"draws":143,"losses":119,"wins":408},"medium":{"draws":201,"losses":192,"wins":279},"none":{"draws":248,"losses":327,"wins":121}},"model_slug":"deepseek-deepseek-v4-1-flash","overall":{"max":75.19336305189155,"mean":39.5737668556252,"min":11.271801424400126},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":30,"overall_ranking_status":"ranked","per_game":{"GB2-01":50.58183366585325,"GB2-02":26.984183127320136,"GB2-03":39.21094528138139,"GB2-04":55.52382996903797,"GB2-05":72.7338376601718,"GB2-06":75.19336305189155,"GB2-07":62.97794411108242,"GB2-08":40.80742778722643},"per_game_all":{"GB2-01":47.487189309537506,"GB2-02":21.792247618070775,"GB2-03":33.31321827560128,"GB2-04":26.37585393167134,"GB2-05":52.198140354096985,"GB2-06":59.09632581110316,"GB2-07":50.259730543069594,"GB2-08":26.067429001850957},"per_game_match_totals_all":{"GB2-01":{"draws":66,"losses":65,"wins":87},"GB2-02":{"draws":204,"losses":28,"wins":46},"GB2-03":{"draws":34,"losses":70,"wins":78},"GB2-04":{"draws":115,"losses":59,"wins":72},"GB2-05":{"draws":0,"losses":109,"wins":127},"GB2-06":{"draws":17,"losses":81,"wins":178},"GB2-07":{"draws":0,"losses":110,"wins":176},"GB2-08":{"draws":156,"losses":116,"wins":44}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":28,"wins":46},"GB2-02":{"draws":57,"losses":8,"wins":23},"GB2-03":{"draws":6,"losses":22,"wins":30},"GB2-04":{"draws":26,"losses":5,"wins":51},"GB2-05":{"draws":0,"losses":9,"wins":67},"GB2-06":{"draws":5,"losses":7,"wins":80},"GB2-07":{"draws":0,"losses":16,"wins":76},"GB2-08":{"draws":49,"losses":24,"wins":35}},"medium":{"GB2-01":{"draws":46,"losses":4,"wins":18},"GB2-02":{"draws":60,"losses":7,"wins":23},"GB2-03":{"draws":10,"losses":19,"wins":31},"GB2-04":{"draws":38,"losses":32,"wins":14},"GB2-05":{"draws":0,"losses":40,"wins":36},"GB2-06":{"draws":8,"losses":7,"wins":79},"GB2-07":{"draws":0,"losses":24,"wins":74},"GB2-08":{"draws":39,"losses":59,"wins":4}},"none":{"GB2-01":{"draws":20,"losses":33,"wins":23},"GB2-02":{"draws":87,"losses":13,"wins":0},"GB2-03":{"draws":18,"losses":29,"wins":17},"GB2-04":{"draws":51,"losses":22,"wins":7},"GB2-05":{"draws":0,"losses":60,"wins":24},"GB2-06":{"draws":4,"losses":67,"wins":19},"GB2-07":{"draws":0,"losses":70,"wins":26},"GB2-08":{"draws":68,"losses":33,"wins":5}}},"per_game_raw_elo_all":{"GB2-01":1570.550759480717,"GB2-02":1523.8657191300329,"GB2-03":1479.019541537941,"GB2-04":1519.4620982989375,"GB2-05":1565.5918898099765,"GB2-06":1657.282538369005,"GB2-07":1564.154512710753,"GB2-08":1356.9588354510913},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1613.2608269926718,"GB2-02":1561.7555095702419,"GB2-03":1542.8733133898322,"GB2-04":1712.5593249631836,"GB2-05":1892.434782069571,"GB2-06":1923.7890812127462,"GB2-07":1754.6299005256376,"GB2-08":1550.5999654523055},"medium":{"GB2-01":1641.1861002345797,"GB2-02":1556.771308630353,"GB2-03":1540.9882420820213,"GB2-04":1425.8959541468055,"GB2-05":1529.6932663496493,"GB2-06":1870.302600353424,"GB2-07":1716.5424355001617,"GB2-08":1210.6336257419828},"none":{"GB2-01":1457.2053512148998,"GB2-02":1453.070339189504,"GB2-03":1353.197069141969,"GB2-04":1419.931015786824,"GB2-05":1274.647621010709,"GB2-06":1177.7559335408441,"GB2-07":1221.2912021064592,"GB2-08":1309.6429151589853}},"per_game_tracks":{"highest":{"GB2-01":50.58183366585325,"GB2-02":26.984183127320136,"GB2-03":39.21094528138139,"GB2-04":55.52382996903797,"GB2-05":72.7338376601718,"GB2-06":75.19336305189155,"GB2-07":62.97794411108242,"GB2-08":40.80742778722643},"medium":{"GB2-01":52.44295115748309,"GB2-02":26.34825360224334,"GB2-03":39.11467185215879,"GB2-04":12.331930401575923,"GB2-05":49.89140451614368,"GB2-06":71.98934050814864,"GB2-07":60.51080360289881,"GB2-08":14.910316416776945},"none":{"GB2-01":39.43678310527615,"GB2-02":12.044306124648847,"GB2-03":21.61403769326364,"GB2-04":11.271801424400126,"GB2-05":33.969178885975495,"GB2-06":30.106273873269323,"GB2-07":27.29044391522753,"GB2-08":22.484542801549498}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":53.001670581745614,"medium":40.942459007178655,"none":24.77717097795133},"reasoning_agg":{"highest":{"max":75.19336305189155,"mean":53.001670581745614,"min":26.984183127320136},"medium":{"max":71.98934050814864,"mean":40.942459007178655,"min":12.331930401575923},"none":{"max":39.43678310527615,"mean":24.77717097795133,"min":11.271801424400126}},"reasoning_labels":{"highest":"Max","medium":"High","none":"None"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":75.19336305189155,"expected_score":39.77055296584001,"reasoning_variance":28.224499603794285,"reliability_score":89.25041161399986,"uncertainty_avg":10.749588386000147,"uncertainty_penalty":0.19678611021480918},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":75.19336305189155,"expected_score":48.438135235713716,"reliability_score":88.8402152039429,"uncertainty_avg":11.159784796057092,"uncertainty_penalty":-4.563535346031898},"medium":{"ceiling_score":71.98934050814864,"expected_score":44.3160655420672,"reliability_score":88.91802708683194,"uncertainty_avg":11.081972913168062,"uncertainty_penalty":3.3736065348885447},"none":{"ceiling_score":39.43678310527615,"expected_score":26.55745811973912,"reliability_score":89.99299255122472,"uncertainty_avg":10.007007448775287,"uncertainty_penalty":1.7802871417877917}}},{"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":4.659586},"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":0.957684}},"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":0.83548},"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":0.957684},"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":39.29100875988175,"highest":42.5420873263483,"medium":39.04266865722575,"none":36.2882702960712},"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":"2026-09-25T16:02:44Z","match_totals_all":{"draws":2055,"losses":2298,"wins":2300},"match_totals_tracks":{"highest":{"draws":620,"losses":784,"wins":862},"medium":{"draws":695,"losses":823,"wins":753},"none":{"draws":740,"losses":691,"wins":685}},"model_slug":"qwen-qwen3-8-max","overall":{"max":90.1443955387162,"mean":38.5215870238904,"min":11.88308300278399},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":31,"overall_ranking_status":"ranked","per_game":{"GB2-01":32.62683857968774,"GB2-02":21.383109438871713,"GB2-03":46.73709363383094,"GB2-04":43.54396182565621,"GB2-05":42.507797739694716,"GB2-06":54.72441106072859,"GB2-07":68.53774121733082,"GB2-08":30.275745114985668},"per_game_all":{"GB2-01":30.799735507409324,"GB2-02":15.279756283863856,"GB2-03":40.04388266404249,"GB2-04":23.843863815213723,"GB2-05":65.06420353009011,"GB2-06":42.699479934742605,"GB2-07":56.34426176095078,"GB2-08":40.25288658274108},"per_game_match_totals_all":{"GB2-01":{"draws":226,"losses":390,"wins":164},"GB2-02":{"draws":635,"losses":99,"wins":44},"GB2-03":{"draws":225,"losses":258,"wins":267},"GB2-04":{"draws":477,"losses":147,"wins":142},"GB2-05":{"draws":0,"losses":294,"wins":507},"GB2-06":{"draws":76,"losses":506,"wins":361},"GB2-07":{"draws":0,"losses":325,"wins":508},"GB2-08":{"draws":416,"losses":279,"wins":307}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":51,"losses":117,"wins":56},"GB2-02":{"draws":198,"losses":30,"wins":33},"GB2-03":{"draws":33,"losses":97,"wins":117},"GB2-04":{"draws":102,"losses":39,"wins":100},"GB2-05":{"draws":0,"losses":179,"wins":141},"GB2-06":{"draws":29,"losses":152,"wins":158},"GB2-07":{"draws":0,"losses":69,"wins":197},"GB2-08":{"draws":207,"losses":101,"wins":60}},"medium":{"GB2-01":{"draws":111,"losses":123,"wins":72},"GB2-02":{"draws":232,"losses":45,"wins":3},"GB2-03":{"draws":72,"losses":84,"wins":94},"GB2-04":{"draws":200,"losses":64,"wins":13},"GB2-05":{"draws":0,"losses":97,"wins":141},"GB2-06":{"draws":27,"losses":162,"wins":161},"GB2-07":{"draws":0,"losses":160,"wins":132},"GB2-08":{"draws":53,"losses":88,"wins":137}},"none":{"GB2-01":{"draws":64,"losses":150,"wins":36},"GB2-02":{"draws":205,"losses":24,"wins":8},"GB2-03":{"draws":120,"losses":77,"wins":56},"GB2-04":{"draws":175,"losses":44,"wins":29},"GB2-05":{"draws":0,"losses":18,"wins":225},"GB2-06":{"draws":20,"losses":192,"wins":42},"GB2-07":{"draws":0,"losses":96,"wins":179},"GB2-08":{"draws":156,"losses":90,"wins":110}}},"per_game_raw_elo_all":{"GB2-01":1316.0657275945862,"GB2-02":1461.0775734456467,"GB2-03":1524.908098551934,"GB2-04":1483.7931846801619,"GB2-05":1749.657876091879,"GB2-06":1367.0220168826997,"GB2-07":1638.1491443727816,"GB2-08":1526.9638364752755},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1343.3023635597492,"GB2-02":1504.294948942284,"GB2-03":1596.2689260067089,"GB2-04":1615.0006829372037,"GB2-05":1389.1819943597798,"GB2-06":1565.1089106507507,"GB2-07":1820.5862524640922,"GB2-08":1394.4072104012434},"medium":{"GB2-01":1426.1685015656856,"GB2-02":1435.9860199294324,"GB2-03":1593.68086849439,"GB2-04":1414.687398706827,"GB2-05":1710.8512444146102,"GB2-06":1501.9072035200847,"GB2-07":1351.9282549861598,"GB2-08":1668.7501849907474},"none":{"GB2-01":1178.7263176583233,"GB2-02":1442.9517514652248,"GB2-03":1384.7745011547036,"GB2-04":1421.6914723964546,"GB2-05":2148.940389501246,"GB2-06":1034.0499364772634,"GB2-07":1741.9329256680928,"GB2-08":1517.7341140338356}},"per_game_tracks":{"highest":{"GB2-01":32.62683857968774,"GB2-02":21.383109438871713,"GB2-03":46.73709363383094,"GB2-04":43.54396182565621,"GB2-05":42.507797739694716,"GB2-06":54.72441106072859,"GB2-07":68.53774121733082,"GB2-08":30.275745114985668},"medium":{"GB2-01":38.84302075911713,"GB2-02":11.88308300278399,"GB2-03":46.508144083646044,"GB2-04":13.567734790878136,"GB2-05":62.54041731185943,"GB2-06":50.92778094014556,"GB2-07":37.20183371033238,"GB2-08":50.86933465904327},"none":{"GB2-01":20.929347183423104,"GB2-02":12.573076409935867,"GB2-03":26.886410274650494,"GB2-04":14.419894829106827,"GB2-05":90.1443955387162,"GB2-06":22.446247803353653,"GB2-07":63.29321035518914,"GB2-08":39.61357997419428}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":40.233822118374256,"medium":39.04266865722575,"none":36.2882702960712},"reasoning_agg":{"highest":{"max":68.53774121733082,"mean":40.233822118374256,"min":21.383109438871713},"medium":{"max":62.54041731185943,"mean":39.04266865722575,"min":11.88308300278399},"none":{"max":90.1443955387162,"mean":36.2882702960712,"min":12.573076409935867}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":90.1443955387162,"expected_score":36.859969311221626,"reasoning_variance":3.9455518223030595,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.6616177126687717},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":68.53774121733082,"expected_score":33.81179020732574,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.422031911048514},"medium":{"ceiling_score":62.54041731185943,"expected_score":39.85971458700528,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.8170459297795318},"none":{"ceiling_score":90.1443955387162,"expected_score":36.90840313933383,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.6201328432626312}}},{"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":3.3421600000000002},"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":0.9739300000000001}},"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":1.4245200000000002},"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":4.096070000000001}},"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":37.078567235002424,"highest":35.45233852196008,"medium":38.90241887186665,"none":36.88094431118054},"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":"2026-09-25T16:16:30Z","match_totals_all":{"draws":2345,"losses":3097,"wins":3100},"match_totals_tracks":{"highest":{"draws":988,"losses":1319,"wins":1181},"medium":{"draws":807,"losses":1195,"wins":1322},"none":{"draws":550,"losses":583,"wins":597}},"model_slug":"claude-opus-4-5","overall":{"max":66.84543135872292,"mean":37.078567235002424,"min":9.818228255319736},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":32,"overall_ranking_status":"ranked","per_game":{"GB2-01":59.326053968020524,"GB2-02":11.142543596266535,"GB2-03":24.4009168781914,"GB2-04":12.573294252110319,"GB2-05":46.23126106901278,"GB2-06":57.899996001122055,"GB2-07":43.723138765545265,"GB2-08":28.321503645411784},"per_game_all":{"GB2-01":49.30567099551132,"GB2-02":12.167200684625454,"GB2-03":27.625725221614392,"GB2-04":16.599777442633734,"GB2-05":46.87497742355405,"GB2-06":48.821165593641105,"GB2-07":41.645695494252074,"GB2-08":53.58832502418728},"per_game_match_totals_all":{"GB2-01":{"draws":320,"losses":293,"wins":438},"GB2-02":{"draws":801,"losses":161,"wins":26},"GB2-03":{"draws":332,"losses":340,"wins":233},"GB2-04":{"draws":529,"losses":210,"wins":115},"GB2-05":{"draws":0,"losses":527,"wins":587},"GB2-06":{"draws":89,"losses":533,"wins":580},"GB2-07":{"draws":0,"losses":685,"wins":587},"GB2-08":{"draws":274,"losses":348,"wins":534}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":56,"losses":104,"wins":197},"GB2-02":{"draws":301,"losses":60,"wins":11},"GB2-03":{"draws":97,"losses":150,"wins":125},"GB2-04":{"draws":245,"losses":138,"wins":54},"GB2-05":{"draws":0,"losses":231,"wins":243},"GB2-06":{"draws":35,"losses":196,"wins":249},"GB2-07":{"draws":0,"losses":245,"wins":253},"GB2-08":{"draws":254,"losses":195,"wins":49}},"medium":{"GB2-01":{"draws":136,"losses":133,"wins":199},"GB2-02":{"draws":308,"losses":67,"wins":5},"GB2-03":{"draws":149,"losses":129,"wins":79},"GB2-04":{"draws":168,"losses":35,"wins":20},"GB2-05":{"draws":0,"losses":215,"wins":235},"GB2-06":{"draws":41,"losses":228,"wins":237},"GB2-07":{"draws":0,"losses":294,"wins":224},"GB2-08":{"draws":5,"losses":94,"wins":323}},"none":{"GB2-01":{"draws":128,"losses":56,"wins":42},"GB2-02":{"draws":192,"losses":34,"wins":10},"GB2-03":{"draws":86,"losses":61,"wins":29},"GB2-04":{"draws":116,"losses":37,"wins":41},"GB2-05":{"draws":0,"losses":81,"wins":109},"GB2-06":{"draws":13,"losses":109,"wins":94},"GB2-07":{"draws":0,"losses":146,"wins":110},"GB2-08":{"draws":15,"losses":59,"wins":162}}},"per_game_raw_elo_all":{"GB2-01":1571.326120110259,"GB2-02":1436.5370575635206,"GB2-03":1391.5144567692125,"GB2-04":1435.6119141526658,"GB2-05":1458.2515236873544,"GB2-06":1466.7307831478217,"GB2-07":1415.0031452746273,"GB2-08":1701.7247112231214},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1710.178254810776,"GB2-02":1427.5767306944488,"GB2-03":1353.9441679487495,"GB2-04":1403.22162299903,"GB2-05":1444.3386272901982,"GB2-06":1614.2310136332721,"GB2-07":1443.7674379150828,"GB2-08":1365.7530278417635},"medium":{"GB2-01":1582.8885398034024,"GB2-02":1429.961299453459,"GB2-03":1447.0595086507585,"GB2-04":1392.5828599891702,"GB2-05":1445.3770803514549,"GB2-06":1430.885554594425,"GB2-07":1483.6761238799647,"GB2-08":1874.6575974676157},"none":{"GB2-01":1420.911565716598,"GB2-02":1452.0731425426543,"GB2-03":1373.539693708129,"GB2-04":1511.031259469797,"GB2-05":1485.0388634204105,"GB2-06":1355.0757812157685,"GB2-07":1317.565874028835,"GB2-08":1864.763508359985}},"per_game_tracks":{"highest":{"GB2-01":59.326053968020524,"GB2-02":11.142543596266535,"GB2-03":24.4009168781914,"GB2-04":12.573294252110319,"GB2-05":46.23126106901278,"GB2-06":57.899996001122055,"GB2-07":43.723138765545265,"GB2-08":28.321503645411784},"medium":{"GB2-01":50.39151672846605,"GB2-02":11.50913920007812,"GB2-03":33.11276640129881,"GB2-04":9.818228255319736,"GB2-05":46.26630148184913,"GB2-06":46.85471815151569,"GB2-07":46.42124939768273,"GB2-08":66.84543135872292},"none":{"GB2-01":38.19944229004737,"GB2-02":13.849919257531704,"GB2-03":25.363492385352973,"GB2-04":27.407809820471147,"GB2-05":48.127369719800235,"GB2-06":41.708782628285576,"GB2-07":34.79269831952821,"GB2-08":65.59804006842714}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":35.45233852196008,"medium":38.90241887186665,"none":36.88094431118054},"reasoning_agg":{"highest":{"max":59.326053968020524,"mean":35.45233852196008,"min":11.142543596266535},"medium":{"max":66.84543135872292,"mean":38.90241887186665,"min":9.818228255319736},"none":{"max":65.59804006842714,"mean":36.88094431118054,"min":13.849919257531704}},"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":66.84543135872292,"expected_score":34.625309978551755,"reasoning_variance":3.450080349906571,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.4532572564506694},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":59.326053968020524,"expected_score":25.728343837377313,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.723994684582767},"medium":{"ceiling_score":66.84543135872292,"expected_score":38.53559485004048,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.3668240218261687},"none":{"ceiling_score":65.59804006842714,"expected_score":39.61199124823747,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.731046937056931}}},{"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":2.8079499999999995},"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":0.4933699999999999},"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":2.80795}},"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":37.01633038301635,"highest":44.793190429889094,"medium":34.630660325327945,"none":31.62514039383202},"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":"2026-09-25T14:44:45Z","match_totals_all":{"draws":2456,"losses":3310,"wins":2947},"match_totals_tracks":{"highest":{"draws":619,"losses":925,"wins":1163},"medium":{"draws":951,"losses":1168,"wins":903},"none":{"draws":886,"losses":1217,"wins":881}},"model_slug":"claude-sonnet-5","overall":{"max":64.64982345476963,"mean":37.01633038301636,"min":9.60693783512406},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":33,"overall_ranking_status":"ranked","per_game":{"GB2-01":55.18882050646197,"GB2-02":13.894809860305726,"GB2-03":46.028376243947854,"GB2-04":29.758173635715277,"GB2-05":54.21419120539835,"GB2-06":36.59176650389889,"GB2-07":58.01956202861504,"GB2-08":64.64982345476963},"per_game_all":{"GB2-01":45.994168171982245,"GB2-02":12.326741654910462,"GB2-03":37.438945964674005,"GB2-04":22.31982580898935,"GB2-05":45.114188356600245,"GB2-06":41.63221924919449,"GB2-07":46.54055985425848,"GB2-08":44.76399400352153},"per_game_match_totals_all":{"GB2-01":{"draws":178,"losses":501,"wins":498},"GB2-02":{"draws":844,"losses":126,"wins":20},"GB2-03":{"draws":368,"losses":394,"wins":307},"GB2-04":{"draws":593,"losses":204,"wins":192},"GB2-05":{"draws":0,"losses":577,"wins":459},"GB2-06":{"draws":61,"losses":591,"wins":442},"GB2-07":{"draws":0,"losses":578,"wins":594},"GB2-08":{"draws":412,"losses":339,"wins":435}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":49,"losses":132,"wins":225},"GB2-02":{"draws":263,"losses":28,"wins":5},"GB2-03":{"draws":106,"losses":112,"wins":97},"GB2-04":{"draws":181,"losses":66,"wins":93},"GB2-05":{"draws":0,"losses":160,"wins":178},"GB2-06":{"draws":18,"losses":215,"wins":95},"GB2-07":{"draws":0,"losses":133,"wins":211},"GB2-08":{"draws":2,"losses":79,"wins":259}},"medium":{"GB2-01":{"draws":67,"losses":170,"wins":134},"GB2-02":{"draws":285,"losses":47,"wins":8},"GB2-03":{"draws":118,"losses":155,"wins":95},"GB2-04":{"draws":205,"losses":86,"wins":58},"GB2-05":{"draws":0,"losses":196,"wins":184},"GB2-06":{"draws":22,"losses":169,"wins":149},"GB2-07":{"draws":0,"losses":211,"wins":223},"GB2-08":{"draws":254,"losses":134,"wins":52}},"none":{"GB2-01":{"draws":62,"losses":199,"wins":139},"GB2-02":{"draws":296,"losses":51,"wins":7},"GB2-03":{"draws":144,"losses":127,"wins":115},"GB2-04":{"draws":207,"losses":52,"wins":41},"GB2-05":{"draws":0,"losses":221,"wins":97},"GB2-06":{"draws":21,"losses":207,"wins":198},"GB2-07":{"draws":0,"losses":234,"wins":160},"GB2-08":{"draws":156,"losses":126,"wins":124}}},"per_game_raw_elo_all":{"GB2-01":1523.2642814469646,"GB2-02":1437.308189344422,"GB2-03":1493.164696456909,"GB2-04":1470.7116507478352,"GB2-05":1429.7838537654625,"GB2-06":1347.6781484432113,"GB2-07":1488.1782388412914,"GB2-08":1584.5738198165327},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1651.1585365823491,"GB2-02":1449.6194687642037,"GB2-03":1585.8305710643456,"GB2-04":1519.6188990359437,"GB2-05":1574.4806021783322,"GB2-06":1265.2546120590778,"GB2-07":1660.705689755907,"GB2-08":1847.9538628823607},"medium":{"GB2-01":1522.6692927335687,"GB2-02":1417.6225297728333,"GB2-03":1409.2724687641871,"GB2-04":1451.5444548730766,"GB2-05":1503.5866413784245,"GB2-06":1420.5099746623619,"GB2-07":1476.3950796409993,"GB2-08":1399.0905055647788},"none":{"GB2-01":1395.965015024976,"GB2-02":1444.6825694962292,"GB2-03":1484.3910495421942,"GB2-04":1440.9715983344856,"GB2-05":1211.2843177396303,"GB2-06":1357.2698586081942,"GB2-07":1327.433947126968,"GB2-08":1506.6770910024586}},"per_game_tracks":{"highest":{"GB2-01":55.18882050646197,"GB2-02":13.894809860305726,"GB2-03":46.028376243947854,"GB2-04":29.758173635715277,"GB2-05":54.21419120539835,"GB2-06":36.59176650389889,"GB2-07":58.01956202861504,"GB2-08":64.64982345476963},"medium":{"GB2-01":45.91146308402966,"GB2-02":9.60693783512406,"GB2-03":29.590881232571984,"GB2-04":19.525005417352162,"GB2-05":49.82748733223222,"GB2-06":45.992692305851016,"GB2-07":45.82465145654429,"GB2-08":30.766163938918144},"none":{"GB2-01":36.882220925455094,"GB2-02":13.478477269301598,"GB2-03":36.69758041750218,"GB2-04":17.67629837390061,"GB2-05":31.300886532170168,"GB2-06":42.31219893783358,"GB2-07":35.77746607761612,"GB2-08":38.87599461687681}},"provider_color":"#C58F68","provider_company":"Anthropic","provider_key":"anthropic","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":44.793190429889094,"medium":34.630660325327945,"none":31.62514039383202},"reasoning_agg":{"highest":{"max":64.64982345476963,"mean":44.793190429889094,"min":13.894809860305726},"medium":{"max":49.82748733223222,"mean":34.630660325327945,"min":9.60693783512406},"none":{"max":42.31219893783358,"mean":31.62514039383202,"min":13.478477269301598}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Thinking disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":64.64982345476963,"expected_score":34.2028911630488,"reasoning_variance":13.168050036057075,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.813439219967563},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":64.64982345476963,"expected_score":36.68243430845297,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.110756121436125},"medium":{"ceiling_score":49.82748733223222,"expected_score":33.425508222522325,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.20515210280562},"none":{"ceiling_score":42.31219893783358,"expected_score":32.50073095817109,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.8755905643390705}}},{"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":0.02748863}},"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":0.027488630000000003}},"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":47.30415802742198,"none":26.59584737354384},"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":"2026-09-25T15:54:55Z","match_totals_all":{"draws":1535,"losses":1531,"wins":1325},"match_totals_tracks":{"medium":{"draws":742,"losses":579,"wins":886},"none":{"draws":793,"losses":952,"wins":439}},"model_slug":"qwen-qwen3-8-flash","overall":{"max":74.00144873524822,"mean":36.95000270048291,"min":8.785005477286392},"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":203,"losses":231,"wins":158},"GB2-02":{"draws":385,"losses":72,"wins":61},"GB2-03":{"draws":134,"losses":162,"wins":187},"GB2-04":{"draws":339,"losses":97,"wins":58},"GB2-05":{"draws":0,"losses":278,"wins":218},"GB2-06":{"draws":47,"losses":190,"wins":365},"GB2-07":{"draws":0,"losses":319,"wins":229},"GB2-08":{"draws":427,"losses":182,"wins":49}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":121,"losses":119,"wins":92},"GB2-02":{"draws":157,"losses":44,"wins":57},"GB2-03":{"draws":49,"losses":62,"wins":122},"GB2-04":{"draws":154,"losses":52,"wins":36},"GB2-05":{"draws":0,"losses":82,"wins":160},"GB2-06":{"draws":37,"losses":50,"wins":179},"GB2-07":{"draws":0,"losses":78,"wins":202},"GB2-08":{"draws":224,"losses":92,"wins":38}},"none":{"GB2-01":{"draws":82,"losses":112,"wins":66},"GB2-02":{"draws":228,"losses":28,"wins":4},"GB2-03":{"draws":85,"losses":100,"wins":65},"GB2-04":{"draws":185,"losses":45,"wins":22},"GB2-05":{"draws":0,"losses":196,"wins":58},"GB2-06":{"draws":10,"losses":140,"wins":186},"GB2-07":{"draws":0,"losses":241,"wins":27},"GB2-08":{"draws":203,"losses":90,"wins":11}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1442.6065705765584,"GB2-02":1529.3998389349945,"GB2-03":1548.579881000369,"GB2-04":1548.878576748059,"GB2-05":1725.532483239105,"GB2-06":1887.0566314718924,"GB2-07":1838.4946857611073,"GB2-08":1396.8902635327127},"none":{"GB2-01":1342.2251301931879,"GB2-02":1414.8842249110578,"GB2-03":1441.4048742590476,"GB2-04":1411.9387944129749,"GB2-05":1165.0488835259146,"GB2-06":1599.2344503904574,"GB2-07":1044.8864063083101,"GB2-08":1321.2787153819802}},"per_game_tracks":{"medium":{"GB2-01":40.08673683836688,"GB2-02":24.898458456294655,"GB2-03":42.1842635007645,"GB2-04":33.57117101283803,"GB2-05":63.47838487808565,"GB2-06":74.00144873524822,"GB2-07":69.77939307553763,"GB2-08":30.43340772224031},"none":{"GB2-01":32.68634905445009,"GB2-02":8.785005477286392,"GB2-03":32.195227382686326,"GB2-04":12.978147131546923,"GB2-05":28.222283900175665,"GB2-06":56.77974293719396,"GB2-07":16.55490280256513,"GB2-08":24.565120302446235}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":47.30415802742198,"none":26.59584737354384},"reasoning_agg":{"medium":{"max":74.00144873524822,"mean":47.30415802742198,"min":24.898458456294655},"none":{"max":56.77974293719396,"mean":26.59584737354384,"min":8.785005477286392}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":74.00144873524822,"reasoning_variance":20.708310653878137},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":74.00144873524822,"expected_score":49.42656456478027,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.1224065373582945},"none":{"ceiling_score":56.77974293719396,"expected_score":27.072320106973386,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.47647273342954577}}},{"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":0.34284062299999996},"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":0.17566728},"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":2.0840289480000003},"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":52.31016653110989,"medium":42.52486126086168,"none":25.81587204834404},"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":"2026-09-25T13:33:49Z","match_totals_all":{"draws":850,"losses":1469,"wins":1570},"match_totals_tracks":{"highest":{"draws":216,"losses":620,"wins":904},"medium":{"draws":238,"losses":700,"wins":577},"none":{"draws":396,"losses":149,"wins":89}},"model_slug":"qwen-qwen3-8-27b","overall":{"max":74.90167026913919,"mean":35.99205923506444,"min":20.202011632004123},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold","fixed_coverage_incomplete","generation_incomplete"],"overall_official_rank":35,"overall_ranking_status":"partial","per_game":{"GB2-01":58.407241304881026,"GB2-04":56.3162952972934,"GB2-05":57.969406483876845,"GB2-06":33.70967503312307,"GB2-07":74.90167026913919,"GB2-08":32.556710798345804},"per_game_match_totals_all":{"GB2-01":{"draws":153,"losses":148,"wins":215},"GB2-03":{"draws":84,"losses":121,"wins":114},"GB2-04":{"draws":248,"losses":117,"wins":193},"GB2-05":{"draws":0,"losses":256,"wins":342},"GB2-06":{"draws":26,"losses":306,"wins":280},"GB2-07":{"draws":0,"losses":316,"wins":304},"GB2-08":{"draws":339,"losses":205,"wins":122}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":8,"losses":81,"wins":157},"GB2-04":{"draws":73,"losses":49,"wins":130},"GB2-05":{"draws":0,"losses":132,"wins":196},"GB2-06":{"draws":17,"losses":155,"wins":92},"GB2-07":{"draws":0,"losses":79,"wins":233},"GB2-08":{"draws":118,"losses":124,"wins":96}},"medium":{"GB2-01":{"draws":145,"losses":67,"wins":58},"GB2-03":{"draws":84,"losses":121,"wins":114},"GB2-05":{"draws":0,"losses":124,"wins":146},"GB2-06":{"draws":9,"losses":151,"wins":188},"GB2-07":{"draws":0,"losses":237,"wins":71}},"none":{"GB2-04":{"draws":175,"losses":68,"wins":63},"GB2-08":{"draws":221,"losses":81,"wins":26}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1701.67334656394,"GB2-04":1699.05144103761,"GB2-05":1634.441721343999,"GB2-06":1220.0562223930833,"GB2-07":1913.6688351436223,"GB2-08":1425.3495104160008},"medium":{"GB2-01":1429.6059149220514,"GB2-03":1537.817412312884,"GB2-05":1484.3666111185962,"GB2-06":1618.1605396285938,"GB2-07":1181.0188896765776},"none":{"GB2-04":1495.9071604016394,"GB2-08":1334.439317034092}},"per_game_tracks":{"highest":{"GB2-01":58.407241304881026,"GB2-04":56.3162952972934,"GB2-05":57.969406483876845,"GB2-06":33.70967503312307,"GB2-07":74.90167026913919,"GB2-08":32.556710798345804},"medium":{"GB2-01":38.98414085011295,"GB2-03":41.52872346510729,"GB2-05":48.37752224301888,"GB2-06":57.945684696607124,"GB2-07":25.78823504946214},"none":{"GB2-04":26.00270887896228,"GB2-08":25.6290352177258}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":48.68009515429089,"medium":39.09407091889831,"none":20.202011632004123},"reasoning_agg":{"highest":{"max":74.90167026913919,"mean":48.68009515429089,"min":32.556710798345804},"medium":{"max":57.945684696607124,"mean":39.09407091889831,"min":25.78823504946214},"none":{"max":26.00270887896228,"mean":20.202011632004123,"min":25.6290352177258}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":74.90167026913919,"reasoning_variance":28.478083522286767},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":74.90167026913919,"expected_score":44.60840262557312,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.071692528717769},"medium":{"ceiling_score":57.945684696607124,"expected_score":42.91953736574567,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.825466446847358},"none":{"ceiling_score":26.00270887896228,"expected_score":23.443153731063216,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.2411420990590933}}},{"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":0.9135725942490001},"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":0.37262013029400004},"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":0.20237245442100005}},"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":0.20237245442100002},"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":1.488565178964},"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":37.55450348986843,"highest":38.51200716437151,"medium":41.259109027909574,"none":29.9857954367799},"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":"2026-09-25T14:59:44Z","match_totals_all":{"draws":1747,"losses":2136,"wins":2117},"match_totals_tracks":{"highest":{"draws":709,"losses":770,"wins":709},"medium":{"draws":471,"losses":803,"wins":962},"none":{"draws":567,"losses":563,"wins":446}},"model_slug":"deepseek-deepseek-v4-pro","overall":{"max":75.28091626993594,"mean":35.89201437659667,"min":9.212833783417654},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":36,"overall_ranking_status":"ranked","per_game":{"GB2-01":22.258235865851287,"GB2-02":10.705367299529621,"GB2-03":33.70168001380781,"GB2-04":21.2316997815558,"GB2-05":45.91113335979322,"GB2-06":75.28091626993594,"GB2-07":72.21134396175917,"GB2-08":26.795680762739188},"per_game_all":{"GB2-01":34.714476951362094,"GB2-03":24.08396099982782,"GB2-04":18.551673986717365,"GB2-05":46.63104376086384,"GB2-07":60.54369388928112,"GB2-08":40.80217135115835},"per_game_match_totals_all":{"GB2-01":{"draws":126,"losses":399,"wins":261},"GB2-02":{"draws":400,"losses":85,"wins":19},"GB2-03":{"draws":304,"losses":298,"wins":196},"GB2-04":{"draws":505,"losses":176,"wins":109},"GB2-05":{"draws":0,"losses":446,"wins":418},"GB2-06":{"draws":25,"losses":230,"wins":335},"GB2-07":{"draws":0,"losses":318,"wins":538},"GB2-08":{"draws":387,"losses":184,"wins":241}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":163,"wins":58},"GB2-02":{"draws":195,"losses":50,"wins":15},"GB2-03":{"draws":135,"losses":104,"wins":85},"GB2-04":{"draws":142,"losses":70,"wins":40},"GB2-05":{"draws":0,"losses":164,"wins":138},"GB2-06":{"draws":20,"losses":61,"wins":179},"GB2-07":{"draws":0,"losses":82,"wins":180},"GB2-08":{"draws":202,"losses":76,"wins":14}},"medium":{"GB2-01":{"draws":23,"losses":124,"wins":161},"GB2-02":{"draws":205,"losses":35,"wins":4},"GB2-03":{"draws":68,"losses":124,"wins":44},"GB2-04":{"draws":169,"losses":75,"wins":48},"GB2-05":{"draws":0,"losses":153,"wins":165},"GB2-06":{"draws":5,"losses":169,"wins":156},"GB2-07":{"draws":0,"losses":83,"wins":165},"GB2-08":{"draws":1,"losses":40,"wins":219}},"none":{"GB2-01":{"draws":88,"losses":112,"wins":42},"GB2-03":{"draws":101,"losses":70,"wins":67},"GB2-04":{"draws":194,"losses":31,"wins":21},"GB2-05":{"draws":0,"losses":129,"wins":115},"GB2-07":{"draws":0,"losses":153,"wins":193},"GB2-08":{"draws":184,"losses":68,"wins":8}}},"per_game_raw_elo_all":{"GB2-01":1370.5535105722947,"GB2-03":1354.5423897738212,"GB2-04":1448.3711010383724,"GB2-05":1455.9773696290085,"GB2-07":1700.6607121877732,"GB2-08":1536.5133552623358},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1197.9967349311883,"GB2-02":1428.5205440495274,"GB2-03":1454.3723474587694,"GB2-04":1466.6180884228831,"GB2-05":1443.8810886057918,"GB2-06":1908.5199707434276,"GB2-07":1875.5836068988096,"GB2-08":1351.119642213177},"medium":{"GB2-01":1572.4251198887735,"GB2-02":1418.717879979862,"GB2-03":1233.2156802078318,"GB2-04":1456.1220332328212,"GB2-05":1578.5191377924639,"GB2-06":1435.9149423027568,"GB2-07":1774.4914466514606,"GB2-08":1952.230032189293},"none":{"GB2-01":1341.2386768969225,"GB2-03":1376.0391416548625,"GB2-04":1422.3731814594128,"GB2-05":1345.5318824887702,"GB2-07":1451.90708301305,"GB2-08":1306.1903913845374}},"per_game_tracks":{"highest":{"GB2-01":22.258235865851287,"GB2-02":10.705367299529621,"GB2-03":33.70168001380781,"GB2-04":21.2316997815558,"GB2-05":45.91113335979322,"GB2-06":75.28091626993594,"GB2-07":72.21134396175917,"GB2-08":26.795680762739188},"medium":{"GB2-01":49.334139920659695,"GB2-02":9.212833783417654,"GB2-03":12.557760361514816,"GB2-04":19.91598677885711,"GB2-05":54.4262704810341,"GB2-06":46.903521988412955,"GB2-07":65.39010876108995,"GB2-08":72.3322501482903},"none":{"GB2-01":32.55105506757531,"GB2-03":25.992442624160834,"GB2-04":14.507335399739189,"GB2-05":39.55572744176421,"GB2-07":44.02962894499428,"GB2-08":23.278583142445555}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.51200716437151,"medium":41.259109027909574,"none":27.904926937508936},"reasoning_agg":{"highest":{"max":75.28091626993594,"mean":38.51200716437151,"min":10.705367299529621},"medium":{"max":72.3322501482903,"mean":41.259109027909574,"min":9.212833783417654},"none":{"max":44.02962894499428,"mean":27.904926937508936,"min":14.507335399739189}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":75.28091626993594,"expected_score":34.62644162160811,"reasoning_variance":13.354182090400638,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.2655727549885611},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":75.28091626993594,"expected_score":29.44508679815904,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.066920366212472},"medium":{"ceiling_score":72.3322501482903,"expected_score":40.50884225256953,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.7502667753400445},"none":{"ceiling_score":44.02962894499428,"expected_score":29.629425222561014,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7244982850520785}}},{"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":0.7756987499999999},"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":0.6137425000000001},"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":34.73343107927787,"highest":41.857588040641794,"medium":37.3173433619514,"none":29.121872292278997},"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":"2026-09-25T13:26:41Z","match_totals_all":{"draws":2032,"losses":2328,"wins":2100},"match_totals_tracks":{"highest":{"draws":592,"losses":737,"wins":865},"medium":{"draws":620,"losses":866,"wins":780},"none":{"draws":820,"losses":725,"wins":455}},"model_slug":"gpt-5-6-terra","overall":{"max":76.93585154551911,"mean":35.78022683442092,"min":12.122561741654145},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":37,"overall_ranking_status":"ranked","per_game":{"GB2-01":65.05600675030205,"GB2-02":30.58419652878032,"GB2-03":29.152984788095484,"GB2-04":14.953275323875648,"GB2-05":49.40159472806108,"GB2-06":76.93585154551911,"GB2-07":40.710585867697205,"GB2-08":28.06620879280346},"per_game_all":{"GB2-01":58.43157959702601,"GB2-02":19.988656070558243,"GB2-03":22.579137142301004,"GB2-04":14.334303751999409,"GB2-06":54.46338973783253,"GB2-07":42.149140036261976,"GB2-08":31.187811218965937},"per_game_match_totals_all":{"GB2-01":{"draws":139,"losses":215,"wins":442},"GB2-02":{"draws":621,"losses":113,"wins":86},"GB2-03":{"draws":334,"losses":241,"wins":99},"GB2-04":{"draws":494,"losses":209,"wins":93},"GB2-05":{"draws":0,"losses":261,"wins":347},"GB2-06":{"draws":51,"losses":377,"wins":410},"GB2-07":{"draws":0,"losses":557,"wins":401},"GB2-08":{"draws":393,"losses":355,"wins":222}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":45,"losses":55,"wins":148},"GB2-02":{"draws":140,"losses":32,"wins":64},"GB2-03":{"draws":97,"losses":73,"wins":50},"GB2-04":{"draws":175,"losses":38,"wins":19},"GB2-05":{"draws":0,"losses":136,"wins":182},"GB2-06":{"draws":22,"losses":47,"wins":173},"GB2-07":{"draws":0,"losses":213,"wins":153},"GB2-08":{"draws":113,"losses":143,"wins":76}},"medium":{"GB2-01":{"draws":2,"losses":65,"wins":179},"GB2-02":{"draws":233,"losses":42,"wins":17},"GB2-03":{"draws":119,"losses":84,"wins":21},"GB2-04":{"draws":147,"losses":106,"wins":47},"GB2-05":{"draws":0,"losses":125,"wins":165},"GB2-06":{"draws":28,"losses":193,"wins":117},"GB2-07":{"draws":0,"losses":122,"wins":144},"GB2-08":{"draws":91,"losses":129,"wins":90}},"none":{"GB2-01":{"draws":92,"losses":95,"wins":115},"GB2-02":{"draws":248,"losses":39,"wins":5},"GB2-03":{"draws":118,"losses":84,"wins":28},"GB2-04":{"draws":172,"losses":65,"wins":27},"GB2-06":{"draws":1,"losses":137,"wins":120},"GB2-07":{"draws":0,"losses":222,"wins":104},"GB2-08":{"draws":189,"losses":83,"wins":56}}},"per_game_raw_elo_all":{"GB2-01":1701.1546810534091,"GB2-02":1493.9207403148303,"GB2-03":1340.48147598197,"GB2-04":1420.3862308164378,"GB2-06":1563.1741934426936,"GB2-07":1424.8693299925092,"GB2-08":1407.814171633394},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1794.308216479141,"GB2-02":1570.9017626387488,"GB2-03":1410.6974052765618,"GB2-04":1426.0809876221997,"GB2-05":1498.726477915025,"GB2-06":1936.8206165711558,"GB2-07":1401.7920865935212,"GB2-08":1366.4041855520484},"medium":{"GB2-01":1762.4363561467956,"GB2-02":1473.6676710089532,"GB2-03":1283.2051660127208,"GB2-04":1411.179558951564,"GB2-05":1643.4520137846655,"GB2-06":1397.4045000243977,"GB2-07":1597.6449502469552,"GB2-08":1412.4743152577723},"none":{"GB2-01":1546.719470534291,"GB2-02":1437.192787296789,"GB2-03":1327.5418566566275,"GB2-04":1423.8981458755488,"GB2-06":1355.2974637325274,"GB2-07":1275.1709531370514,"GB2-08":1444.564014090361}},"per_game_tracks":{"highest":{"GB2-01":65.05600675030205,"GB2-02":30.58419652878032,"GB2-03":29.152984788095484,"GB2-04":14.953275323875648,"GB2-05":49.40159472806108,"GB2-06":76.93585154551911,"GB2-07":40.710585867697205,"GB2-08":28.06620879280346},"medium":{"GB2-01":62.7636226124865,"GB2-02":17.25920994124026,"GB2-03":17.192155362935345,"GB2-04":13.179346281696866,"GB2-05":58.44890987380218,"GB2-06":44.59328944547627,"GB2-07":53.59577102591772,"GB2-08":31.506442352056098},"none":{"GB2-01":47.475109428289485,"GB2-02":12.122561741654145,"GB2-03":21.392271275872172,"GB2-04":14.870289650425716,"GB2-06":41.861028222502206,"GB2-07":32.141063215171016,"GB2-08":33.99078251203825}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.857588040641794,"medium":37.3173433619514,"none":28.16574910066959},"reasoning_agg":{"highest":{"max":76.93585154551911,"mean":41.857588040641794,"min":14.953275323875648},"medium":{"max":62.7636226124865,"mean":37.3173433619514,"min":13.179346281696866},"none":{"max":47.475109428289485,"mean":28.16574910066959,"min":12.122561741654145}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":76.93585154551911,"expected_score":31.741642824172864,"reasoning_variance":13.691838939972204,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.038584010248059},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.93585154551911,"expected_score":33.87839371802946,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.9791943226123365},"medium":{"ceiling_score":62.7636226124865,"expected_score":36.30090254349116,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0164408184602394},"none":{"ceiling_score":47.475109428289485,"expected_score":30.44717176912876,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.2814226684591716}}},{"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":1.1725616482799999},"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":0.98845232184},"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":0.21636246784}},"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":0.98845232184},"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":1.1725616482799999}},"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":37.47963062697469,"highest":41.51017966504621,"medium":36.03872592479018,"none":31.779004608881248},"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":"2026-09-25T16:20:12Z","match_totals_all":{"draws":1868,"losses":2168,"wins":2014},"match_totals_tracks":{"highest":{"draws":627,"losses":658,"wins":913},"medium":{"draws":657,"losses":880,"wins":781},"none":{"draws":584,"losses":630,"wins":320}},"model_slug":"deepseek-deepseek-v4-pro-0813","overall":{"max":71.8729308953561,"mean":35.707533898763096,"min":8.629972723433358},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":38,"overall_ranking_status":"ranked","per_game":{"GB2-01":41.654809510966054,"GB2-02":9.851281775273819,"GB2-03":47.221073631451,"GB2-04":14.07171218097534,"GB2-05":69.9800600901681,"GB2-06":59.08933985378316,"GB2-07":71.8729308953561,"GB2-08":18.340229382396092},"per_game_all":{"GB2-01":40.03098577976187,"GB2-03":36.73688709515567,"GB2-04":13.727826588776681,"GB2-06":52.863164512342614,"GB2-07":55.9431182407325,"GB2-08":25.575801545078786},"per_game_match_totals_all":{"GB2-01":{"draws":273,"losses":301,"wins":262},"GB2-02":{"draws":401,"losses":105,"wins":16},"GB2-03":{"draws":197,"losses":318,"wins":277},"GB2-04":{"draws":454,"losses":264,"wins":116},"GB2-05":{"draws":0,"losses":176,"wins":340},"GB2-06":{"draws":34,"losses":423,"wins":415},"GB2-07":{"draws":0,"losses":324,"wins":478},"GB2-08":{"draws":509,"losses":257,"wins":110}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":11,"losses":108,"wins":131},"GB2-02":{"draws":225,"losses":41,"wins":8},"GB2-03":{"draws":27,"losses":83,"wins":132},"GB2-04":{"draws":167,"losses":99,"wins":56},"GB2-05":{"draws":0,"losses":60,"wins":188},"GB2-06":{"draws":12,"losses":106,"wins":194},"GB2-07":{"draws":0,"losses":58,"wins":202},"GB2-08":{"draws":185,"losses":103,"wins":2}},"medium":{"GB2-01":{"draws":202,"losses":70,"wins":70},"GB2-02":{"draws":176,"losses":64,"wins":8},"GB2-03":{"draws":48,"losses":159,"wins":107},"GB2-04":{"draws":93,"losses":102,"wins":41},"GB2-05":{"draws":0,"losses":116,"wins":152},"GB2-06":{"draws":19,"losses":179,"wins":108},"GB2-07":{"draws":0,"losses":78,"wins":200},"GB2-08":{"draws":119,"losses":112,"wins":95}},"none":{"GB2-01":{"draws":60,"losses":123,"wins":61},"GB2-03":{"draws":122,"losses":76,"wins":38},"GB2-04":{"draws":194,"losses":63,"wins":19},"GB2-06":{"draws":3,"losses":138,"wins":113},"GB2-07":{"draws":0,"losses":188,"wins":76},"GB2-08":{"draws":205,"losses":42,"wins":13}}},"per_game_raw_elo_all":{"GB2-01":1444.042690107898,"GB2-03":1489.2028432585175,"GB2-04":1415.8486109583084,"GB2-06":1536.095888543575,"GB2-07":1632.615070290699,"GB2-08":1335.1281273657835},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1467.8060324709397,"GB2-02":1421.8172875640382,"GB2-03":1601.6780053004868,"GB2-04":1416.2924084625038,"GB2-05":1828.4690903656574,"GB2-06":1638.2933466880772,"GB2-07":1870.6286447706118,"GB2-08":1239.8410226636497},"medium":{"GB2-01":1511.1313317362046,"GB2-02":1424.736386569079,"GB2-03":1424.901306966007,"GB2-04":1383.967405873055,"GB2-05":1454.8185414839636,"GB2-06":1356.4627200228902,"GB2-07":1868.5979423021952,"GB2-08":1435.7025958077024},"none":{"GB2-01":1353.1907061165489,"GB2-03":1441.0292175090588,"GB2-04":1447.2860185393665,"GB2-06":1613.531598919758,"GB2-07":1158.6186237992895,"GB2-08":1329.8407636259985}},"per_game_tracks":{"highest":{"GB2-01":41.654809510966054,"GB2-02":9.851281775273819,"GB2-03":47.221073631451,"GB2-04":14.07171218097534,"GB2-05":69.9800600901681,"GB2-06":59.08933985378316,"GB2-07":71.8729308953561,"GB2-08":18.340229382396092},"medium":{"GB2-01":45.02267217841239,"GB2-02":10.089425367998915,"GB2-03":30.898756018461224,"GB2-04":8.629972723433358,"GB2-05":46.51115385299343,"GB2-06":42.053752059801255,"GB2-07":71.79125135121897,"GB2-08":33.3128238460019},"none":{"GB2-01":33.41547564990715,"GB2-03":32.090831635554785,"GB2-04":18.481794861921347,"GB2-06":57.44640162344343,"GB2-07":24.165172475622438,"GB2-08":25.074351406838364}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.51017966504621,"medium":36.03872592479018,"none":29.57369610645291},"reasoning_agg":{"highest":{"max":71.8729308953561,"mean":41.51017966504621,"min":9.851281775273819},"medium":{"max":71.79125135121897,"mean":36.03872592479018,"min":8.629972723433358},"none":{"max":57.44640162344343,"mean":29.57369610645291,"min":18.481794861921347}},"reasoning_labels":{"highest":"Max","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":71.8729308953561,"expected_score":34.29549102243437,"reasoning_variance":11.936483558593299,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.4120428763287265},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":71.8729308953561,"expected_score":32.98876413195392,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.521415533092288},"medium":{"ceiling_score":71.79125135121897,"expected_score":35.2028485482261,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.8358773765640777},"none":{"ceiling_score":57.44640162344343,"expected_score":32.662525188985576,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.0888290825326656}}},{"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":1.4469687303},"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":0.013816857666666668,"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":0.527165994},"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":0.20593804349999997},"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":0.013816857666666668,"recorded_attempt_count":72,"run_count":48,"total":3.5146565168000006},"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":33.91133708337776,"highest":34.185104021864404,"medium":37.25084999448105,"none":30.29805723378784},"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":"2026-09-25T14:05:48Z","match_totals_all":{"draws":3727,"losses":3961,"wins":3240},"match_totals_tracks":{"highest":{"draws":661,"losses":841,"wins":584},"medium":{"draws":1318,"losses":1154,"wins":1186},"none":{"draws":1748,"losses":1966,"wins":1470}},"model_slug":"z-ai-glm-5-2","overall":{"max":73.77006751900642,"mean":33.91133708337777,"min":7.705163219117038},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":39,"overall_ranking_status":"ranked","per_game":{"GB2-01":47.13787652878352,"GB2-02":33.03910046349824,"GB2-03":31.24083392559777,"GB2-04":33.06169697877685,"GB2-05":54.502993109011314,"GB2-06":45.628065333452454,"GB2-07":7.705163219117038,"GB2-08":21.16510261667805},"per_game_all":{"GB2-01":35.01204240840615,"GB2-02":19.554249985060085,"GB2-03":26.315428403009946,"GB2-04":23.997787081500707,"GB2-05":48.27351440600811,"GB2-06":55.20638776159378,"GB2-07":37.11508385759718,"GB2-08":25.816202763846135},"per_game_match_totals_all":{"GB2-01":{"draws":433,"losses":542,"wins":359},"GB2-02":{"draws":1059,"losses":162,"wins":129},"GB2-03":{"draws":515,"losses":397,"wins":176},"GB2-04":{"draws":758,"losses":333,"wins":233},"GB2-05":{"draws":0,"losses":752,"wins":596},"GB2-06":{"draws":94,"losses":482,"wins":802},"GB2-07":{"draws":0,"losses":843,"wins":723},"GB2-08":{"draws":868,"losses":450,"wins":222}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":112,"losses":91,"wins":117},"GB2-02":{"draws":122,"losses":34,"wins":78},"GB2-03":{"draws":118,"losses":68,"wins":46},"GB2-04":{"draws":88,"losses":88,"wins":72},"GB2-05":{"draws":0,"losses":132,"wins":110},"GB2-06":{"draws":12,"losses":117,"wins":133},"GB2-07":{"draws":0,"losses":236,"wins":26},"GB2-08":{"draws":209,"losses":75,"wins":2}},"medium":{"GB2-01":{"draws":170,"losses":133,"wins":117},"GB2-02":{"draws":354,"losses":62,"wins":46},"GB2-03":{"draws":195,"losses":146,"wins":17},"GB2-04":{"draws":259,"losses":108,"wins":77},"GB2-05":{"draws":0,"losses":232,"wins":258},"GB2-06":{"draws":24,"losses":98,"wins":360},"GB2-07":{"draws":0,"losses":208,"wins":304},"GB2-08":{"draws":316,"losses":167,"wins":7}},"none":{"GB2-01":{"draws":151,"losses":318,"wins":125},"GB2-02":{"draws":583,"losses":66,"wins":5},"GB2-03":{"draws":202,"losses":183,"wins":113},"GB2-04":{"draws":411,"losses":137,"wins":84},"GB2-05":{"draws":0,"losses":388,"wins":228},"GB2-06":{"draws":58,"losses":267,"wins":309},"GB2-07":{"draws":0,"losses":399,"wins":393},"GB2-08":{"draws":343,"losses":208,"wins":213}}},"per_game_raw_elo_all":{"GB2-01":1375.9336987925037,"GB2-02":1493.0199148373765,"GB2-03":1382.6918545570807,"GB2-04":1486.2791844007909,"GB2-05":1484.9644288380266,"GB2-06":1577.219576937345,"GB2-07":1351.8673585109618,"GB2-08":1339.4499688115468},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1541.3621536320004,"GB2-02":1588.4441487763484,"GB2-03":1432.2081191859868,"GB2-04":1545.1922997177962,"GB2-05":1583.0018170020317,"GB2-06":1417.476853557659,"GB2-07":913.1207086604495,"GB2-08":1277.207605245957},"medium":{"GB2-01":1360.6184657082804,"GB2-02":1477.3398409819695,"GB2-03":1311.0856388682455,"GB2-04":1476.1221922986085,"GB2-05":1570.0079400312711,"GB2-06":1884.5188350448484,"GB2-07":1648.0406863345377,"GB2-08":1272.3808804357977},"none":{"GB2-01":1225.8204770372306,"GB2-02":1413.2757547538108,"GB2-03":1404.7818056170095,"GB2-04":1437.5230611859683,"GB2-05":1301.8835294807768,"GB2-06":1429.6630422095277,"GB2-07":1494.4406805378987,"GB2-08":1468.7614207528857}},"per_game_tracks":{"highest":{"GB2-01":47.13787652878352,"GB2-02":33.03910046349824,"GB2-03":31.24083392559777,"GB2-04":33.06169697877685,"GB2-05":54.502993109011314,"GB2-06":45.628065333452454,"GB2-07":7.705163219117038,"GB2-08":21.16510261667805},"medium":{"GB2-01":33.792694938604896,"GB2-02":17.36870095915482,"GB2-03":19.44145855258766,"GB2-04":22.404154835140126,"GB2-05":53.641190570473,"GB2-06":73.77006751900642,"GB2-07":56.93627466574622,"GB2-08":20.652257915135223},"none":{"GB2-01":24.10555575783004,"GB2-02":8.254948532527202,"GB2-03":28.263992730844407,"GB2-04":16.527509430585145,"GB2-05":36.676359538540034,"GB2-06":46.221030432322465,"GB2-07":46.703813687928275,"GB2-08":35.631247759725134}},"provider_color":"#2563EB","provider_company":"Zhipu","provider_key":"z-ai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.185104021864404,"medium":37.25084999448105,"none":30.29805723378784},"reasoning_agg":{"highest":{"max":54.502993109011314,"mean":34.185104021864404,"min":7.705163219117038},"medium":{"max":73.77006751900642,"mean":37.25084999448105,"min":17.36870095915482},"none":{"max":46.703813687928275,"mean":30.29805723378784,"min":8.254948532527202}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":73.77006751900642,"expected_score":31.0312665979771,"reasoning_variance":6.95279276069321,"reliability_score":99.98224431818181,"uncertainty_avg":0.01775568181818186,"uncertainty_penalty":-2.8800704854006653},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.502993109011314,"expected_score":24.56037065741548,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.624733364448925},"medium":{"ceiling_score":73.77006751900642,"expected_score":37.54324766329288,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.29239766881183016},"none":{"ceiling_score":46.703813687928275,"expected_score":30.990181473222933,"reliability_score":99.94673295454545,"uncertainty_avg":0.05326704545454558,"uncertainty_penalty":0.6921242394350919}}},{"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":2.2561124999999995},"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":0.779305},"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":2.2561124999999995}},"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":4.455918750000001},"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":37.49580919330325,"highest":38.34190463573641,"medium":34.43999991037422,"none":31.56397705047057},"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":"2026-09-25T12:56:44Z","match_totals_all":{"draws":1233,"losses":1396,"wins":1305},"match_totals_tracks":{"highest":{"draws":538,"losses":521,"wins":561},"medium":{"draws":414,"losses":548,"wins":516},"none":{"draws":281,"losses":327,"wins":228}},"model_slug":"gpt-5","overall":{"max":70.82103497731079,"mean":33.674922707272515,"min":3.1304801359516308},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings","fixed_coverage_incomplete"],"overall_official_rank":40,"overall_ranking_status":"partial","per_game":{"GB2-01":33.22556272805624,"GB2-02":10.851384971598858,"GB2-03":21.82884738650803,"GB2-04":18.492108948060444,"GB2-05":69.49263343872869,"GB2-06":70.82103497731079,"GB2-07":57.62738467323732,"GB2-08":24.396279962390953},"per_game_all":{"GB2-01":36.20265875575295,"GB2-03":13.761571463173803,"GB2-05":58.3350324417224,"GB2-07":53.486509745615415,"GB2-08":25.693273560251697},"per_game_match_totals_all":{"GB2-01":{"draws":61,"losses":275,"wins":170},"GB2-02":{"draws":279,"losses":59,"wins":14},"GB2-03":{"draws":133,"losses":184,"wins":51},"GB2-04":{"draws":303,"losses":92,"wins":55},"GB2-05":{"draws":0,"losses":182,"wins":298},"GB2-06":{"draws":26,"losses":145,"wins":253},"GB2-07":{"draws":0,"losses":255,"wins":401},"GB2-08":{"draws":431,"losses":204,"wins":63}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":21,"losses":101,"wins":78},"GB2-02":{"draws":159,"losses":28,"wins":13},"GB2-03":{"draws":54,"losses":62,"wins":26},"GB2-04":{"draws":149,"losses":46,"wins":17},"GB2-05":{"draws":0,"losses":56,"wins":116},"GB2-06":{"draws":10,"losses":49,"wins":135},"GB2-07":{"draws":0,"losses":93,"wins":143},"GB2-08":{"draws":145,"losses":86,"wins":33}},"medium":{"GB2-01":{"draws":27,"losses":134,"wins":33},"GB2-03":{"draws":58,"losses":55,"wins":19},"GB2-04":{"draws":154,"losses":46,"wins":38},"GB2-05":{"draws":0,"losses":64,"wins":126},"GB2-06":{"draws":16,"losses":96,"wins":118},"GB2-07":{"draws":0,"losses":77,"wins":169},"GB2-08":{"draws":159,"losses":76,"wins":13}},"none":{"GB2-01":{"draws":13,"losses":40,"wins":59},"GB2-02":{"draws":120,"losses":31,"wins":1},"GB2-03":{"draws":21,"losses":67,"wins":6},"GB2-05":{"draws":0,"losses":62,"wins":56},"GB2-07":{"draws":0,"losses":85,"wins":89},"GB2-08":{"draws":127,"losses":42,"wins":17}}},"per_game_raw_elo_all":{"GB2-01":1398.0071548654396,"GB2-03":1256.4313789713876,"GB2-05":1650.2026602076128,"GB2-07":1598.7588976743439,"GB2-08":1339.6231830955949},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1353.2005538627475,"GB2-02":1433.0118488111527,"GB2-03":1339.318229141879,"GB2-04":1450.7282264128946,"GB2-05":1825.7911435000174,"GB2-06":1838.5649567775201,"GB2-07":1659.3017330955558,"GB2-08":1320.722949607299},"medium":{"GB2-01":1126.8105583111628,"GB2-03":1282.0012952043824,"GB2-04":1426.5988635252065,"GB2-05":1665.6221882023112,"GB2-06":1496.290841930129,"GB2-07":1687.9165793259276,"GB2-08":1307.6036854276551},"none":{"GB2-01":1714.0103524224082,"GB2-02":1425.6050675512174,"GB2-03":1147.9746125679014,"GB2-05":1459.1946489205093,"GB2-07":1449.0583806015484,"GB2-08":1390.5429142518308}},"per_game_tracks":{"highest":{"GB2-01":33.22556272805624,"GB2-02":10.851384971598858,"GB2-03":21.82884738650803,"GB2-04":18.492108948060444,"GB2-05":69.49263343872869,"GB2-06":70.82103497731079,"GB2-07":57.62738467323732,"GB2-08":24.396279962390953},"medium":{"GB2-01":16.963732521903303,"GB2-03":16.325386867061756,"GB2-04":15.08141203859531,"GB2-05":59.499000328638054,"GB2-06":50.28851664089777,"GB2-07":59.58082426309626,"GB2-08":23.341126712427066},"none":{"GB2-01":58.418681017299306,"GB2-02":9.227503285322296,"GB2-03":3.1304801359516308,"GB2-05":46.01346355780045,"GB2-07":43.25132030051264,"GB2-08":29.342414005937076}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":38.34190463573641,"medium":33.30927307032606,"none":29.373590415755064},"reasoning_agg":{"highest":{"max":70.82103497731079,"mean":38.34190463573641,"min":10.851384971598858},"medium":{"max":59.58082426309626,"mean":33.30927307032606,"min":15.08141203859531},"none":{"max":58.418681017299306,"mean":29.373590415755064,"min":3.1304801359516308}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":70.82103497731079,"expected_score":34.98868678135884,"reasoning_variance":8.968314219981348,"reliability_score":99.13867427501012,"uncertainty_avg":0.8613257249898757,"uncertainty_penalty":1.313764074086322},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":70.82103497731079,"expected_score":29.813693148369243,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.52821148736717},"medium":{"ceiling_score":59.58082426309626,"expected_score":34.18455369463296,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.8752806243069031},"none":{"ceiling_score":58.418681017299306,"expected_score":34.10670141099322,"reliability_score":97.84668568752531,"uncertainty_avg":2.153314312474689,"uncertainty_penalty":4.733110995238153}}},{"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":1.0777302951999999},"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":0.25360068319999995}},"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":1.3313309783999998},"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":42.12357564467531,"none":28.551607363877064},"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":"2026-09-25T12:52:57Z","match_totals_all":{"draws":794,"losses":1265,"wins":1087},"match_totals_tracks":{"medium":{"draws":322,"losses":644,"wins":670},"none":{"draws":472,"losses":621,"wins":417}},"model_slug":"xiaomi-mimo-v2-5-pro","overall":{"max":68.29746038794151,"mean":33.40730558412735,"min":4.615901320625215},"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":41,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":103,"losses":226,"wins":291},"GB2-02":{"draws":180,"losses":35,"wins":13},"GB2-03":{"draws":81,"losses":55,"wins":28},"GB2-04":{"draws":122,"losses":44,"wins":54},"GB2-05":{"draws":0,"losses":278,"wins":146},"GB2-06":{"draws":7,"losses":188,"wins":275},"GB2-07":{"draws":0,"losses":284,"wins":272},"GB2-08":{"draws":301,"losses":155,"wins":8}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":43,"losses":121,"wins":230},"GB2-04":{"draws":122,"losses":44,"wins":54},"GB2-05":{"draws":0,"losses":143,"wins":73},"GB2-06":{"draws":2,"losses":66,"wins":180},"GB2-07":{"draws":0,"losses":175,"wins":131},"GB2-08":{"draws":155,"losses":95,"wins":2}},"none":{"GB2-01":{"draws":60,"losses":105,"wins":61},"GB2-02":{"draws":180,"losses":35,"wins":13},"GB2-03":{"draws":81,"losses":55,"wins":28},"GB2-05":{"draws":0,"losses":135,"wins":73},"GB2-06":{"draws":5,"losses":122,"wins":95},"GB2-07":{"draws":0,"losses":109,"wins":141},"GB2-08":{"draws":146,"losses":60,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1747.7486728929528,"GB2-04":1498.002911542282,"GB2-05":1271.5826941372475,"GB2-06":1793.4876526516734,"GB2-07":1431.8861416519917,"GB2-08":1253.5592248137123},"none":{"GB2-01":1409.2533977452536,"GB2-02":1386.9531513092209,"GB2-03":1307.8369821715016,"GB2-05":1173.139299796228,"GB2-06":1330.8761528680536,"GB2-07":1504.46710023982,"GB2-08":1300.6831239572457}},"per_game_tracks":{"medium":{"GB2-01":62.09238331960013,"GB2-04":25.703543197148946,"GB2-05":34.79835154781813,"GB2-06":68.29746038794151,"GB2-07":42.59689833921164,"GB2-08":19.252817076331517},"none":{"GB2-01":37.36361428580678,"GB2-02":4.615901320625215,"GB2-03":19.08692079482323,"GB2-05":28.566789813099383,"GB2-06":40.26936162900415,"GB2-07":47.29932137115699,"GB2-08":22.6593423326237}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":39.200404177689705,"none":27.614206990565},"reasoning_agg":{"medium":{"max":68.29746038794151,"mean":39.200404177689705,"min":19.252817076331517},"none":{"max":47.29932137115699,"mean":27.614206990565,"min":4.615901320625215}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":68.29746038794151,"reasoning_variance":11.586197187124707},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":68.29746038794151,"expected_score":43.8619507611948,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.661546583505093},"none":{"ceiling_score":47.29932137115699,"expected_score":28.59632341538502,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.9821164248200205}}},{"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":0.0939199},"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":0.0306889},"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":0.016316724999999997}},"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":0.030688899999999998},"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":32.857441590301384,"highest":43.62895753236266,"medium":30.12942170206434,"none":25.376707397121997},"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":"2026-09-25T14:22:13Z","match_totals_all":{"draws":530,"losses":924,"wins":586},"match_totals_tracks":{"highest":{"draws":98,"losses":261,"wins":337},"medium":{"draws":216,"losses":344,"wins":148},"none":{"draws":216,"losses":319,"wins":101}},"model_slug":"gpt-6-luna","overall":{"max":76.68636345470857,"mean":33.045028877183,"min":10.200783051786512},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["generation_incomplete"],"overall_official_rank":42,"overall_ranking_status":"partial","per_game":{"GB2-01":32.577483197926895,"GB2-02":35.736737545406314,"GB2-03":27.32497239731715,"GB2-04":36.761198585719725,"GB2-05":51.82887430033942,"GB2-06":76.68636345470857,"GB2-07":35.2583774058522,"GB2-08":52.85765337163106},"per_game_all":{"GB2-01":30.404176042732377,"GB2-02":19.248746546938303,"GB2-03":28.599917611640336,"GB2-04":24.158077674390455,"GB2-05":49.613082892584224,"GB2-06":46.525447201053794,"GB2-08":31.452643162770197},"per_game_match_totals_all":{"GB2-01":{"draws":43,"losses":147,"wins":58},"GB2-02":{"draws":210,"losses":49,"wins":37},"GB2-03":{"draws":26,"losses":101,"wins":55},"GB2-04":{"draws":133,"losses":80,"wins":49},"GB2-05":{"draws":0,"losses":126,"wins":130},"GB2-06":{"draws":18,"losses":166,"wins":106},"GB2-07":{"draws":0,"losses":116,"wins":76},"GB2-08":{"draws":100,"losses":139,"wins":75}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":52,"wins":26},"GB2-02":{"draws":49,"losses":9,"wins":34},"GB2-03":{"draws":3,"losses":40,"wins":19},"GB2-04":{"draws":33,"losses":17,"wins":30},"GB2-05":{"draws":0,"losses":36,"wins":50},"GB2-06":{"draws":9,"losses":13,"wins":78},"GB2-07":{"draws":0,"losses":61,"wins":35},"GB2-08":{"draws":4,"losses":33,"wins":65}},"medium":{"GB2-01":{"draws":29,"losses":39,"wins":16},"GB2-02":{"draws":77,"losses":23,"wins":2},"GB2-03":{"draws":13,"losses":31,"wins":18},"GB2-04":{"draws":49,"losses":28,"wins":11},"GB2-05":{"draws":0,"losses":36,"wins":44},"GB2-06":{"draws":9,"losses":73,"wins":16},"GB2-07":{"draws":0,"losses":55,"wins":41},"GB2-08":{"draws":39,"losses":59,"wins":0}},"none":{"GB2-01":{"draws":14,"losses":56,"wins":16},"GB2-02":{"draws":84,"losses":17,"wins":1},"GB2-03":{"draws":10,"losses":30,"wins":18},"GB2-04":{"draws":51,"losses":35,"wins":8},"GB2-05":{"draws":0,"losses":54,"wins":36},"GB2-06":{"draws":0,"losses":80,"wins":12},"GB2-08":{"draws":57,"losses":47,"wins":10}}},"per_game_raw_elo_all":{"GB2-01":1329.3919325334898,"GB2-02":1504.52841465587,"GB2-03":1428.8617415845408,"GB2-04":1503.4852141186286,"GB2-05":1522.7760233457448,"GB2-06":1448.1630305715134,"GB2-08":1428.0554830837484},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1360.9508017642634,"GB2-02":1622.9847755272187,"GB2-03":1414.7374212036264,"GB2-04":1588.7967516245444,"GB2-05":1557.7608692446993,"GB2-06":1946.831431122891,"GB2-07":1340.176559634495,"GB2-08":1710.4022553306731},"medium":{"GB2-01":1368.9606199703867,"GB2-02":1451.0091397204333,"GB2-03":1451.6104458381499,"GB2-04":1478.212853956462,"GB2-05":1518.543125364701,"GB2-06":1239.8605732376068,"GB2-07":1447.3198602798677,"GB2-08":1266.9720176074093},"none":{"GB2-01":1258.2643758658196,"GB2-02":1439.591328719958,"GB2-03":1420.2373577118456,"GB2-04":1443.4460367748802,"GB2-05":1492.0240754278334,"GB2-06":1157.797087354043,"GB2-08":1306.792176313163}},"per_game_tracks":{"highest":{"GB2-01":32.577483197926895,"GB2-02":35.736737545406314,"GB2-03":27.32497239731715,"GB2-04":36.761198585719725,"GB2-05":51.82887430033942,"GB2-06":76.68636345470857,"GB2-07":35.2583774058522,"GB2-08":52.85765337163106},"medium":{"GB2-01":33.2677047708935,"GB2-02":11.808719043622077,"GB2-03":30.790788087810803,"GB2-04":20.377750187081375,"GB2-05":49.2610359164719,"GB2-06":33.96181958467115,"GB2-07":42.43933485308878,"GB2-08":19.12822117287516},"none":{"GB2-01":25.36734015937674,"GB2-02":10.200783051786512,"GB2-03":27.683992349793055,"GB2-04":15.335284250370272,"GB2-05":47.74933846094135,"GB2-06":28.928158563781658,"GB2-08":22.372054943804372}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":43.62895753236266,"medium":30.12942170206434,"none":25.376707397121997},"reasoning_agg":{"highest":{"max":76.68636345470857,"mean":43.62895753236266,"min":27.32497239731715},"medium":{"max":49.2610359164719,"mean":30.12942170206434,"min":11.808719043622077},"none":{"max":47.74933846094135,"mean":25.376707397121997,"min":10.200783051786512}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":76.68636345470857,"expected_score":31.305965424183515,"reasoning_variance":18.252250135240665,"reliability_score":90.17950079319978,"uncertainty_avg":9.820499206800221,"uncertainty_penalty":-1.7390634529994848},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":76.68636345470857,"expected_score":37.63087803303994,"reliability_score":89.99464092618325,"uncertainty_avg":10.005359073816752,"uncertainty_penalty":-5.998079499322721},"medium":{"ceiling_score":49.2610359164719,"expected_score":30.581892597331606,"reliability_score":90.4600379329718,"uncertainty_avg":9.5399620670282,"uncertainty_penalty":0.4524708952672647},"none":{"ceiling_score":47.74933846094135,"expected_score":26.899650833275125,"reliability_score":90.87106703865615,"uncertainty_avg":9.128932961343844,"uncertainty_penalty":1.5229434361531275}}},{"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":0.18239875000000003}},"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":0.9112225},"codegen_latency_ms":{"attempt_count":24,"max_ms":500731,"mean_ms":212687.25,"min_ms":38716,"run_count":16},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":500731,"mean_ms":358367.875,"min_ms":131800,"run_count":8},"none":{"attempt_count":9,"max_ms":115558,"mean_ms":67006.625,"min_ms":38716,"run_count":8}},"codegen_output_tokens":{"attempt_count":24,"output_max":27099,"output_mean":11144.8125,"output_min":1575,"run_count":16},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":27099,"output_mean":19189.625,"output_min":6698,"run_count":8},"none":{"attempt_count":9,"output_max":5506,"output_mean":3100.0,"output_min":1575,"run_count":8}},"display_name":"Qwen3.7 Max","economics":{"medium":33.82068922880934,"none":33.870933140137396},"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":"2026-09-25T14:33:45Z","match_totals_all":{"draws":1060,"losses":1133,"wins":966},"match_totals_tracks":{"medium":{"draws":588,"losses":545,"wins":526},"none":{"draws":472,"losses":588,"wins":440}},"model_slug":"qwen-qwen3-7-max","overall":{"max":72.93190187054188,"mean":32.734592623814834,"min":10.664384932466085},"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":111,"losses":157,"wins":122},"GB2-02":{"draws":365,"losses":60,"wins":33},"GB2-03":{"draws":93,"losses":45,"wins":12},"GB2-04":{"draws":146,"losses":47,"wins":42},"GB2-05":{"draws":0,"losses":247,"wins":213},"GB2-06":{"draws":25,"losses":252,"wins":187},"GB2-07":{"draws":0,"losses":122,"wins":332},"GB2-08":{"draws":320,"losses":203,"wins":25}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":60,"losses":120,"wins":22},"GB2-02":{"draws":201,"losses":33,"wins":10},"GB2-04":{"draws":146,"losses":47,"wins":42},"GB2-05":{"draws":0,"losses":124,"wins":110},"GB2-06":{"draws":23,"losses":83,"wins":128},"GB2-07":{"draws":0,"losses":36,"wins":196},"GB2-08":{"draws":158,"losses":102,"wins":18}},"none":{"GB2-01":{"draws":51,"losses":37,"wins":100},"GB2-02":{"draws":164,"losses":27,"wins":23},"GB2-03":{"draws":93,"losses":45,"wins":12},"GB2-05":{"draws":0,"losses":123,"wins":103},"GB2-06":{"draws":2,"losses":169,"wins":59},"GB2-07":{"draws":0,"losses":86,"wins":136},"GB2-08":{"draws":162,"losses":101,"wins":7}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1116.7667296118393,"GB2-02":1449.3219932683191,"GB2-04":1397.5002555098133,"GB2-05":1391.5900684076817,"GB2-06":1602.9709274369272,"GB2-07":1887.874488266294,"GB2-08":1317.166016388608},"none":{"GB2-01":1720.3951004144337,"GB2-02":1463.5097112982878,"GB2-03":1322.0768677527358,"GB2-05":1373.0131556037793,"GB2-06":1057.325050187689,"GB2-07":1627.6300514217016,"GB2-08":1283.4622351785426}},"per_game_tracks":{"medium":{"GB2-01":16.28451698383895,"GB2-02":13.522719036613323,"GB2-04":10.664384932466085,"GB2-05":42.42220503142851,"GB2-06":56.7454811145915,"GB2-07":72.93190187054188,"GB2-08":24.17361563218513},"none":{"GB2-01":59.48821171455273,"GB2-02":15.277846845543255,"GB2-03":20.29269496662492,"GB2-05":41.223683029145114,"GB2-06":23.775390810505247,"GB2-07":55.45085414085405,"GB2-08":21.587850473736427}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":32.71029546692019,"none":32.75888978070947},"reasoning_agg":{"medium":{"max":72.93190187054188,"mean":32.71029546692019,"min":10.664384932466085},"none":{"max":59.48821171455273,"mean":32.75888978070947,"min":15.277846845543255}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":72.93190187054188,"reasoning_variance":0.04859431378927326},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":72.93190187054188,"expected_score":34.1404003673106,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.430104900390404},"none":{"ceiling_score":59.48821171455273,"expected_score":35.15635011657616,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.3974603358666897}}},{"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":0.24666659999999996},"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":0.05054444999999999},"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":0.0367878}},"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":0.050544450000000005},"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":0.0367878},"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":0.33399884999999996},"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":31.471409490295727,"highest":41.84697249364046,"medium":32.903427472866106,"none":19.663828504380618},"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":"2026-09-25T15:41:54Z","match_totals_all":{"draws":2685,"losses":3268,"wins":2205},"match_totals_tracks":{"highest":{"draws":914,"losses":760,"wins":1068},"medium":{"draws":953,"losses":1091,"wins":806},"none":{"draws":818,"losses":1417,"wins":331}},"model_slug":"gpt-5-6-luna","overall":{"max":81.2042772769244,"mean":31.471409490295727,"min":8.701180641503443},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":44,"overall_ranking_status":"ranked","per_game":{"GB2-01":63.01830422379207,"GB2-02":12.781594766493846,"GB2-03":26.96684174359192,"GB2-04":11.007260933312008,"GB2-05":53.18526830022632,"GB2-06":81.2042772769244,"GB2-07":64.43923630535639,"GB2-08":22.172996399426747},"per_game_all":{"GB2-01":42.66779267347959,"GB2-02":13.060713372661944,"GB2-03":24.908105572699096,"GB2-04":17.389226372747398,"GB2-05":42.78037634511116,"GB2-06":54.45995746109898,"GB2-07":38.47522515982528,"GB2-08":18.02987896474238},"per_game_match_totals_all":{"GB2-01":{"draws":132,"losses":482,"wins":417},"GB2-02":{"draws":819,"losses":104,"wins":23},"GB2-03":{"draws":487,"losses":400,"wins":171},"GB2-04":{"draws":609,"losses":198,"wins":111},"GB2-05":{"draws":0,"losses":558,"wins":501},"GB2-06":{"draws":80,"losses":466,"wins":530},"GB2-07":{"draws":0,"losses":619,"wins":411},"GB2-08":{"draws":558,"losses":441,"wins":41}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":0,"losses":84,"wins":232},"GB2-02":{"draws":256,"losses":25,"wins":15},"GB2-03":{"draws":173,"losses":142,"wins":68},"GB2-04":{"draws":185,"losses":82,"wins":33},"GB2-05":{"draws":0,"losses":191,"wins":245},"GB2-06":{"draws":43,"losses":48,"wins":236},"GB2-07":{"draws":0,"losses":109,"wins":233},"GB2-08":{"draws":257,"losses":79,"wins":6}},"medium":{"GB2-01":{"draws":60,"losses":204,"wins":143},"GB2-02":{"draws":297,"losses":47,"wins":6},"GB2-03":{"draws":135,"losses":144,"wins":88},"GB2-04":{"draws":207,"losses":55,"wins":44},"GB2-05":{"draws":0,"losses":154,"wins":159},"GB2-06":{"draws":17,"losses":162,"wins":232},"GB2-07":{"draws":0,"losses":230,"wins":116},"GB2-08":{"draws":237,"losses":95,"wins":18}},"none":{"GB2-01":{"draws":72,"losses":194,"wins":42},"GB2-02":{"draws":266,"losses":32,"wins":2},"GB2-03":{"draws":179,"losses":114,"wins":15},"GB2-04":{"draws":217,"losses":61,"wins":34},"GB2-05":{"draws":0,"losses":213,"wins":97},"GB2-06":{"draws":20,"losses":256,"wins":62},"GB2-07":{"draws":0,"losses":280,"wins":62},"GB2-08":{"draws":64,"losses":267,"wins":17}}},"per_game_raw_elo_all":{"GB2-01":1478.3621907490533,"GB2-02":1443.0250665007616,"GB2-03":1359.9686514607681,"GB2-04":1438.8455331706639,"GB2-05":1392.6480369198823,"GB2-06":1560.2100628525843,"GB2-07":1369.1159665239265,"GB2-08":1233.7585742168112},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1763.003514868158,"GB2-02":1441.7146270238864,"GB2-03":1380.944398778814,"GB2-04":1396.7896230760327,"GB2-05":1555.550717864032,"GB2-06":2003.9172974884755,"GB2-07":1756.5529772065865,"GB2-08":1288.4683412899717},"medium":{"GB2-01":1395.931270627249,"GB2-02":1467.298834098546,"GB2-03":1407.26332903877,"GB2-04":1512.447010417425,"GB2-05":1385.740228490143,"GB2-06":1583.0758348930235,"GB2-07":1248.0929858646862,"GB2-08":1301.9500960874611},"none":{"GB2-01":1276.1517867517532,"GB2-02":1420.0617383798524,"GB2-03":1291.6982265647202,"GB2-04":1407.2999660185344,"GB2-05":1236.6531644054721,"GB2-06":1093.6370561762542,"GB2-07":1102.7019365005071,"GB2-08":1110.857285273001}},"per_game_tracks":{"highest":{"GB2-01":63.01830422379207,"GB2-02":12.781594766493846,"GB2-03":26.96684174359192,"GB2-04":11.007260933312008,"GB2-05":53.18526830022632,"GB2-06":81.2042772769244,"GB2-07":64.43923630535639,"GB2-08":22.172996399426747},"medium":{"GB2-01":36.892139986097995,"GB2-02":16.646470580801548,"GB2-03":29.399378159658458,"GB2-04":28.499312490995,"GB2-05":42.275479635114195,"GB2-06":55.929576936759275,"GB2-07":30.369602140205416,"GB2-08":23.215459853296952},"none":{"GB2-01":28.092933810548693,"GB2-02":9.754074770690439,"GB2-03":18.358096814846906,"GB2-04":12.66110569393519,"GB2-05":32.88038109999295,"GB2-06":26.246018169613286,"GB2-07":20.616837033914027,"GB2-08":8.701180641503443}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":41.84697249364046,"medium":32.903427472866106,"none":19.663828504380618},"reasoning_agg":{"highest":{"max":81.2042772769244,"mean":41.84697249364046,"min":11.007260933312008},"medium":{"max":55.929576936759275,"mean":32.903427472866106,"min":16.646470580801548},"none":{"max":32.88038109999295,"mean":19.663828504380618,"min":8.701180641503443}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":81.2042772769244,"expected_score":27.805664209969436,"reasoning_variance":22.18314398925984,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.6657452803262913},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":81.2042772769244,"expected_score":33.531260988915,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.315711504725456},"medium":{"ceiling_score":55.929576936759275,"expected_score":32.00181630243413,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.9016111704319769},"none":{"ceiling_score":32.88038109999295,"expected_score":17.883915338559174,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.7799131658214442}}},{"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":0.457564}},"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":30.876939936900786},"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":"2026-09-25T15:54:23Z","match_totals_all":{"draws":620,"losses":670,"wins":517},"match_totals_tracks":{"none":{"draws":620,"losses":670,"wins":517}},"model_slug":"gpt-4-1","overall":{"max":53.67468803008354,"mean":30.876939936900786,"min":6.9862813021302},"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":45,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":16,"losses":70,"wins":113},"GB2-02":{"draws":211,"losses":32,"wins":1},"GB2-03":{"draws":42,"losses":68,"wins":58},"GB2-04":{"draws":162,"losses":53,"wins":11},"GB2-05":{"draws":0,"losses":166,"wins":42},"GB2-06":{"draws":19,"losses":93,"wins":124},"GB2-07":{"draws":0,"losses":121,"wins":135},"GB2-08":{"draws":170,"losses":67,"wins":33}},"per_game_match_totals_tracks":{"none":{"GB2-01":{"draws":16,"losses":70,"wins":113},"GB2-02":{"draws":211,"losses":32,"wins":1},"GB2-03":{"draws":42,"losses":68,"wins":58},"GB2-04":{"draws":162,"losses":53,"wins":11},"GB2-05":{"draws":0,"losses":166,"wins":42},"GB2-06":{"draws":19,"losses":93,"wins":124},"GB2-07":{"draws":0,"losses":121,"wins":135},"GB2-08":{"draws":170,"losses":67,"wins":33}}},"per_game_raw_elo_tracks":{"none":{"GB2-01":1638.496353573131,"GB2-02":1441.3652676206952,"GB2-03":1463.2483969765071,"GB2-04":1373.6441886130692,"GB2-05":983.6847562803387,"GB2-06":1455.3995689204392,"GB2-07":1520.7906560666256,"GB2-08":1359.142480613769}},"per_game_tracks":{"none":{"GB2-01":53.67468803008354,"GB2-02":12.402197288141299,"GB2-03":33.72939172603578,"GB2-04":6.9862813021302,"GB2-05":16.636523889428613,"GB2-06":47.838972097614196,"GB2-07":48.413228051643856,"GB2-08":27.334237110128832}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"none":30.876939936900786},"reasoning_agg":{"none":{"max":53.67468803008354,"mean":30.876939936900786,"min":6.9862813021302}},"reasoning_labels":{"highest":"Setting not tested","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":53.67468803008354},"score_diagnostics_by_reasoning":{"none":{"ceiling_score":53.67468803008354,"expected_score":32.05501430881509,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.1780743719143025}}},{"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":1.2830031539999998}},"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":1.2830031539999998}},"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":1.2830031539999998},"codegen_latency_ms":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":18,"max_ms":1108247,"mean_ms":850298.125,"min_ms":548194,"run_count":8}},"codegen_output_tokens":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":18,"output_max":56063,"output_mean":38535.375,"output_min":23283,"run_count":8}},"display_name":"Kimi K2.7 Code","economics":{"medium":32.88244772696924},"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":"2026-09-25T13:33:44Z","match_totals_all":{"draws":390,"losses":458,"wins":510},"match_totals_tracks":{"medium":{"draws":390,"losses":458,"wins":510}},"model_slug":"moonshotai-kimi-k2-7-code","overall":{"max":51.93262612726081,"mean":30.600565633888362,"min":10.785004751134416},"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":46,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":7,"losses":100,"wins":93},"GB2-02":{"draws":193,"losses":40,"wins":11},"GB2-04":{"draws":165,"losses":41,"wins":18},"GB2-05":{"draws":0,"losses":95,"wins":105},"GB2-07":{"draws":0,"losses":110,"wins":134},"GB2-08":{"draws":25,"losses":72,"wins":149}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":7,"losses":100,"wins":93},"GB2-02":{"draws":193,"losses":40,"wins":11},"GB2-04":{"draws":165,"losses":41,"wins":18},"GB2-05":{"draws":0,"losses":95,"wins":105},"GB2-07":{"draws":0,"losses":110,"wins":134},"GB2-08":{"draws":25,"losses":72,"wins":149}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1344.1626289780015,"GB2-02":1445.4985349638378,"GB2-04":1398.9282390844303,"GB2-05":1544.7377882000017,"GB2-07":1422.3985733716686,"GB2-08":1622.4143031272313}},"per_game_tracks":{"medium":{"GB2-01":32.577592074565786,"GB2-02":12.984272900063827,"GB2-04":10.785004751134416,"GB2-05":51.93262612726081,"GB2-07":41.77833026164878,"GB2-08":47.23686024714184}},"provider_color":"#7C3AED","provider_company":"Moonshot","provider_key":"moonshotai","provider_text_color":"#faf5ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.600565633888362},"reasoning_agg":{"medium":{"max":51.93262612726081,"mean":30.600565633888362,"min":10.785004751134416}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":51.93262612726081},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":51.93262612726081,"expected_score":34.44381224805107,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.8432466141627053}}},{"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":0.08840574999999999,"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":0.08840574999999999,"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}},"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":0.0865375,"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":4.2016860000000005},"codegen_latency_ms":{"attempt_count":29,"max_ms":130647,"mean_ms":59683.958333333336,"min_ms":17534,"run_count":24},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":8,"max_ms":39668,"mean_ms":28324.375,"min_ms":19788,"run_count":8},"medium":{"attempt_count":8,"max_ms":79649,"mean_ms":42263.5,"min_ms":17534,"run_count":8},"none":{"attempt_count":13,"max_ms":130647,"mean_ms":108464.0,"min_ms":46796,"run_count":8}},"codegen_output_tokens":{"attempt_count":69,"output_max":15813,"output_mean":8194.3125,"output_min":2653,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":40,"output_max":15813,"output_mean":9014.65625,"output_min":4501,"run_count":32},"medium":{"attempt_count":8,"output_max":6616,"output_mean":4172.125,"output_min":2653,"run_count":8},"none":{"attempt_count":21,"output_max":14517,"output_mean":8935.125,"output_min":5431,"run_count":8}},"display_name":"O3","economics":{"all":36.43598741889812,"highest":39.689127494925586,"medium":37.121648482195226,"none":26.37225226289518},"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":"2026-09-25T15:14:18Z","match_totals_all":{"draws":1676,"losses":5072,"wins":4262},"match_totals_tracks":{"highest":{"draws":846,"losses":3675,"wins":3439},"medium":{"draws":385,"losses":519,"wins":524},"none":{"draws":445,"losses":878,"wins":299}},"model_slug":"o3","overall":{"max":52.03780039623947,"mean":30.520487489208833,"min":8.861174993521987},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":47,"overall_ranking_status":"partial","per_game":{"GB2-01":44.356829595027115,"GB2-03":18.275114149122885,"GB2-05":52.03780039623947,"GB2-06":45.38071106501111,"GB2-07":42.31127094485157,"GB2-08":35.77303881930137},"per_game_all":{"GB2-01":31.33031336011707,"GB2-06":40.17970583910605,"GB2-07":43.77339254938681,"GB2-08":30.46053792698254},"per_game_match_totals_all":{"GB2-01":{"draws":261,"losses":781,"wins":626},"GB2-03":{"draws":124,"losses":180,"wins":90},"GB2-04":{"draws":180,"losses":36,"wins":14},"GB2-05":{"draws":0,"losses":854,"wins":961},"GB2-06":{"draws":109,"losses":1325,"wins":973},"GB2-07":{"draws":0,"losses":1321,"wins":1205},"GB2-08":{"draws":1002,"losses":575,"wins":393}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":111,"losses":434,"wins":533},"GB2-03":{"draws":124,"losses":180,"wins":90},"GB2-05":{"draws":0,"losses":744,"wins":851},"GB2-06":{"draws":34,"losses":932,"wins":801},"GB2-07":{"draws":0,"losses":1017,"wins":851},"GB2-08":{"draws":577,"losses":368,"wins":313}},"medium":{"GB2-01":{"draws":37,"losses":90,"wins":71},"GB2-04":{"draws":180,"losses":36,"wins":14},"GB2-05":{"draws":0,"losses":110,"wins":110},"GB2-06":{"draws":22,"losses":108,"wins":118},"GB2-07":{"draws":0,"losses":94,"wins":152},"GB2-08":{"draws":146,"losses":81,"wins":59}},"none":{"GB2-01":{"draws":113,"losses":257,"wins":22},"GB2-06":{"draws":53,"losses":285,"wins":54},"GB2-07":{"draws":0,"losses":210,"wins":202},"GB2-08":{"draws":279,"losses":126,"wins":21}}},"per_game_raw_elo_all":{"GB2-01":1321.7539305404491,"GB2-06":1324.126507881416,"GB2-07":1447.8479775059113,"GB2-08":1396.8657194328946},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1501.3202629319196,"GB2-03":1288.1863481775406,"GB2-05":1538.2139081889095,"GB2-06":1407.7523429759424,"GB2-07":1423.3727009046795,"GB2-08":1465.5589447123277},"medium":{"GB2-01":1360.0647950863756,"GB2-04":1385.834382821887,"GB2-05":1511.9103472929748,"GB2-06":1466.4237574789388,"GB2-07":1574.3007031258494,"GB2-08":1389.6689339264644},"none":{"GB2-01":1103.876733603052,"GB2-06":1098.203423189367,"GB2-07":1345.8705284872053,"GB2-08":1335.3692796598912}},"per_game_tracks":{"highest":{"GB2-01":44.356829595027115,"GB2-03":18.275114149122885,"GB2-05":52.03780039623947,"GB2-06":45.38071106501111,"GB2-07":42.31127094485157,"GB2-08":35.77303881930137},"medium":{"GB2-01":33.707552632427934,"GB2-04":8.861174993521987,"GB2-05":49.94772634864385,"GB2-06":48.543105104646564,"GB2-07":51.966061908297576,"GB2-08":29.704269905633453},"none":{"GB2-01":15.926557852896163,"GB2-06":26.615301347660477,"GB2-07":37.04284479501129,"GB2-08":25.904305056012785}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":34.83954362218033,"medium":34.545586455410955,"none":22.176332390035217},"reasoning_agg":{"highest":{"max":52.03780039623947,"mean":34.83954362218033,"min":18.275114149122885},"medium":{"max":51.966061908297576,"mean":34.545586455410955,"min":8.861174993521987},"none":{"max":37.04284479501129,"mean":22.176332390035217,"min":15.926557852896163}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":52.03780039623947,"expected_score":31.645498363679334,"reasoning_variance":12.663211232145112,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.125010874470501},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":52.03780039623947,"expected_score":28.432834446492194,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.406709175688135},"medium":{"ceiling_score":51.966061908297576,"expected_score":38.20647888381805,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.660892428407095},"none":{"ceiling_score":37.04284479501129,"expected_score":22.731172268799348,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.5548398787641311}}},{"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":0.42810399999999993},"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":0.16760900000000004}},"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":0.4057699999999999}},"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":1.0014830000000001},"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":31.663062858469946,"highest":32.015952753786415,"medium":35.14408027758309,"none":24.18388960192967},"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":"2026-09-25T14:13:55Z","match_totals_all":{"draws":1792,"losses":2417,"wins":1563},"match_totals_tracks":{"highest":{"draws":768,"losses":854,"wins":620},"medium":{"draws":486,"losses":658,"wins":594},"none":{"draws":538,"losses":905,"wins":349}},"model_slug":"bytedance-seed-seed-2-0-code","overall":{"max":75.43253351935807,"mean":29.798693064342945,"min":6.506552449736231},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":48,"overall_ranking_status":"ranked","per_game":{"GB2-01":39.31602941916818,"GB2-02":8.075838704215268,"GB2-03":28.37320291516669,"GB2-04":6.506552449736231,"GB2-05":54.55419811458228,"GB2-06":25.175682332360164,"GB2-07":52.83609631342515,"GB2-08":41.29002178163735},"per_game_all":{"GB2-01":36.60514300971939,"GB2-03":27.492825037895056,"GB2-04":12.48681085515961,"GB2-05":41.63904769793038,"GB2-06":24.95335050470993,"GB2-08":46.801200045405324},"per_game_match_totals_all":{"GB2-01":{"draws":245,"losses":316,"wins":169},"GB2-02":{"draws":416,"losses":62,"wins":4},"GB2-03":{"draws":251,"losses":370,"wins":229},"GB2-04":{"draws":530,"losses":125,"wins":65},"GB2-05":{"draws":0,"losses":451,"wins":353},"GB2-06":{"draws":5,"losses":567,"wins":156},"GB2-07":{"draws":0,"losses":345,"wins":273},"GB2-08":{"draws":345,"losses":181,"wins":314}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":133,"losses":68,"wins":49},"GB2-02":{"draws":208,"losses":25,"wins":1},"GB2-03":{"draws":109,"losses":121,"wins":72},"GB2-04":{"draws":164,"losses":47,"wins":19},"GB2-05":{"draws":0,"losses":163,"wins":161},"GB2-06":{"draws":1,"losses":181,"wins":58},"GB2-07":{"draws":0,"losses":182,"wins":168},"GB2-08":{"draws":153,"losses":67,"wins":92}},"medium":{"GB2-01":{"draws":46,"losses":102,"wins":102},"GB2-02":{"draws":208,"losses":37,"wins":3},"GB2-03":{"draws":56,"losses":131,"wins":59},"GB2-04":{"draws":173,"losses":48,"wins":23},"GB2-05":{"draws":0,"losses":102,"wins":148},"GB2-06":{"draws":2,"losses":195,"wins":45},"GB2-08":{"draws":1,"losses":43,"wins":214}},"none":{"GB2-01":{"draws":66,"losses":146,"wins":18},"GB2-03":{"draws":86,"losses":118,"wins":98},"GB2-04":{"draws":193,"losses":30,"wins":23},"GB2-05":{"draws":0,"losses":186,"wins":44},"GB2-06":{"draws":2,"losses":191,"wins":53},"GB2-07":{"draws":0,"losses":163,"wins":105},"GB2-08":{"draws":191,"losses":71,"wins":8}}},"per_game_raw_elo_all":{"GB2-01":1397.729812576142,"GB2-03":1389.9313491850546,"GB2-04":1409.3107766557794,"GB2-05":1377.6448982065606,"GB2-06":1076.1358156245058,"GB2-08":1615.1460414611745},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1435.1846187113122,"GB2-02":1411.1822389925464,"GB2-03":1398.4737461688474,"GB2-04":1370.2351489145487,"GB2-05":1580.3429566189945,"GB2-06":1079.957238668903,"GB2-07":1583.1810602596506,"GB2-08":1541.2520417101243},"medium":{"GB2-01":1556.2246491961014,"GB2-02":1418.6064511381016,"GB2-03":1356.1997656077283,"GB2-04":1426.0389380006973,"GB2-05":1505.392215434343,"GB2-06":1068.6933279372302,"GB2-08":1993.1563562965605},"none":{"GB2-01":1201.7801698210126,"GB2-03":1415.1205357785889,"GB2-04":1431.6582430520918,"GB2-05":1047.1995225663443,"GB2-06":1079.7568802673843,"GB2-07":1265.6389751628028,"GB2-08":1311.029726376838}},"per_game_tracks":{"highest":{"GB2-01":39.31602941916818,"GB2-02":8.075838704215268,"GB2-03":28.37320291516669,"GB2-04":6.506552449736231,"GB2-05":54.55419811458228,"GB2-06":25.175682332360164,"GB2-07":52.83609631342515,"GB2-08":41.29002178163735},"medium":{"GB2-01":47.99394925717289,"GB2-02":9.226164992898436,"GB2-03":24.1673833049802,"GB2-04":15.045013366680111,"GB2-05":49.641747320730154,"GB2-06":24.50177018126175,"GB2-08":75.43253351935807},"none":{"GB2-01":22.505450352817086,"GB2-03":29.93788889353827,"GB2-04":15.908866749062488,"GB2-05":20.721197658478708,"GB2-06":25.18259900050788,"GB2-07":31.350179723882725,"GB2-08":23.681044835220536}},"provider_color":"#F44336","provider_company":"ByteDance","provider_key":"bytedance-seed","provider_text_color":"#fff8f8","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":32.015952753786415,"medium":33.990237218869844,"none":23.389889220372577},"reasoning_agg":{"highest":{"max":54.55419811458228,"mean":32.015952753786415,"min":6.506552449736231},"medium":{"max":75.43253351935807,"mean":33.990237218869844,"min":9.226164992898436},"none":{"max":31.350179723882725,"mean":23.389889220372577,"min":15.908866749062488}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":75.43253351935807,"expected_score":26.75616777530225,"reasoning_variance":10.600347998497266,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.0425252890406966},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.55419811458228,"expected_score":21.82044393638153,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.195508817404885},"medium":{"ceiling_score":75.43253351935807,"expected_score":33.47933359497677,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.5109036238930713},"none":{"ceiling_score":31.350179723882725,"expected_score":22.35113452834438,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.0387546920281956}}},{"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":2.01516825},"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":37.21858849121705,"none":21.94285654112259},"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":"2026-09-25T15:14:25Z","match_totals_all":{"draws":1258,"losses":1266,"wins":879},"match_totals_tracks":{"medium":{"draws":528,"losses":565,"wins":656},"none":{"draws":730,"losses":701,"wins":223}},"model_slug":"gpt-5-4-mini","overall":{"max":60.753181324378254,"mean":29.58072251616982,"min":0.0},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":49,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":87,"losses":129,"wins":156},"GB2-02":{"draws":380,"losses":52,"wins":6},"GB2-03":{"draws":200,"losses":65,"wins":40},"GB2-04":{"draws":290,"losses":77,"wins":83},"GB2-05":{"draws":0,"losses":232,"wins":164},"GB2-06":{"draws":35,"losses":202,"wins":203},"GB2-07":{"draws":0,"losses":345,"wins":155},"GB2-08":{"draws":266,"losses":164,"wins":72}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":12,"losses":54,"wins":122},"GB2-02":{"draws":180,"losses":30,"wins":6},"GB2-03":{"draws":74,"losses":52,"wins":35},"GB2-04":{"draws":142,"losses":32,"wins":48},"GB2-05":{"draws":0,"losses":92,"wins":120},"GB2-06":{"draws":25,"losses":77,"wins":124},"GB2-07":{"draws":0,"losses":121,"wins":135},"GB2-08":{"draws":95,"losses":107,"wins":66}},"none":{"GB2-01":{"draws":75,"losses":75,"wins":34},"GB2-02":{"draws":200,"losses":22,"wins":0},"GB2-03":{"draws":126,"losses":13,"wins":5},"GB2-04":{"draws":148,"losses":45,"wins":35},"GB2-05":{"draws":0,"losses":140,"wins":44},"GB2-06":{"draws":10,"losses":125,"wins":79},"GB2-07":{"draws":0,"losses":224,"wins":20},"GB2-08":{"draws":171,"losses":57,"wins":6}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1738.0389555080314,"GB2-02":1420.5307445622263,"GB2-03":1420.9895234122694,"GB2-04":1486.7428807986598,"GB2-05":1490.6265842785156,"GB2-06":1490.6696003044897,"GB2-07":1529.4570672951763,"GB2-08":1348.6382865503635},"none":{"GB2-01":1383.239729616377,"GB2-02":1429.788805327151,"GB2-03":1448.666548535275,"GB2-04":1435.0070834621893,"GB2-05":1070.9035033771586,"GB2-06":1244.0923632699235,"GB2-07":799.04601452757,"GB2-08":1320.1696200624187}},"per_game_tracks":{"medium":{"GB2-01":60.753181324378254,"GB2-02":9.242992989536942,"GB2-03":29.69551968181914,"GB2-04":24.02215444542085,"GB2-05":48.57592667595412,"GB2-06":49.9350548600679,"GB2-07":48.994068196362356,"GB2-08":26.529809756196794},"none":{"GB2-01":35.293552338742806,"GB2-02":10.598572345430599,"GB2-03":32.12861045665751,"GB2-04":16.266226481322114,"GB2-05":22.019261559659135,"GB2-06":34.9978767970118,"GB2-07":0.0,"GB2-08":24.23875235015678}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":37.21858849121705,"none":21.94285654112259},"reasoning_agg":{"medium":{"max":60.753181324378254,"mean":37.21858849121705,"min":9.242992989536942},"none":{"max":35.293552338742806,"mean":21.94285654112259,"min":0.0}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":60.753181324378254,"reasoning_variance":15.275731950094457},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":60.753181324378254,"expected_score":36.932977655827635,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.2856108353894129},"none":{"ceiling_score":35.293552338742806,"expected_score":22.163484686738716,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.22062814561612498}}},{"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":0.3954491500000001},"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":0.39544914999999997},"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":0.14744575},"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":1.0821378999999998},"codegen_latency_ms":{"attempt_count":55,"max_ms":2131860,"mean_ms":191027.9411764706,"min_ms":20868,"run_count":34},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":3,"max_ms":2131860,"mean_ms":1627538.0,"min_ms":1123216,"run_count":2},"medium":{"attempt_count":25,"max_ms":1064325,"mean_ms":157709.5,"min_ms":63447,"run_count":16},"none":{"attempt_count":27,"max_ms":101610,"mean_ms":44782.625,"min_ms":20868,"run_count":16}},"codegen_output_tokens":{"attempt_count":55,"output_max":256000,"output_mean":22146.529411764706,"output_min":2711,"run_count":34},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":3,"output_max":256000,"output_mean":192000.0,"output_min":128000,"run_count":2},"medium":{"attempt_count":25,"output_max":25344,"output_mean":17769.9375,"output_min":11435,"run_count":16},"none":{"attempt_count":27,"output_max":10894,"output_mean":5291.4375,"output_min":2711,"run_count":16}},"display_name":"GPT-5.4 Nano","economics":{"medium":33.12559705121601,"none":27.883782722007982},"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":"2026-09-25T14:31:41Z","match_totals_all":{"draws":1238,"losses":2297,"wins":1673},"match_totals_tracks":{"medium":{"draws":512,"losses":1160,"wins":1004},"none":{"draws":726,"losses":1137,"wins":669}},"model_slug":"gpt-5-4-nano","overall":{"max":57.82115624580523,"mean":28.387812633883797,"min":10.4996181061563},"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":147,"losses":397,"wins":182},"GB2-02":{"draws":571,"losses":92,"wins":7},"GB2-03":{"draws":57,"losses":63,"wins":34},"GB2-04":{"draws":121,"losses":32,"wins":69},"GB2-05":{"draws":0,"losses":532,"wins":278},"GB2-06":{"draws":19,"losses":391,"wins":490},"GB2-07":{"draws":0,"losses":494,"wins":254},"GB2-08":{"draws":323,"losses":296,"wins":359}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":54,"losses":258,"wins":52},"GB2-02":{"draws":191,"losses":25,"wins":0},"GB2-04":{"draws":121,"losses":32,"wins":69},"GB2-05":{"draws":0,"losses":198,"wins":216},"GB2-06":{"draws":18,"losses":174,"wins":286},"GB2-07":{"draws":0,"losses":306,"wins":186},"GB2-08":{"draws":128,"losses":167,"wins":195}},"none":{"GB2-01":{"draws":93,"losses":139,"wins":130},"GB2-02":{"draws":380,"losses":67,"wins":7},"GB2-03":{"draws":57,"losses":63,"wins":34},"GB2-05":{"draws":0,"losses":334,"wins":62},"GB2-06":{"draws":1,"losses":217,"wins":204},"GB2-07":{"draws":0,"losses":188,"wins":68},"GB2-08":{"draws":195,"losses":129,"wins":164}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1066.6378423386482,"GB2-02":1431.2084405501407,"GB2-04":1523.4178925941112,"GB2-05":1488.8605390108578,"GB2-06":1620.5154003824932,"GB2-07":1280.7711885492126,"GB2-08":1532.9577130546695},"none":{"GB2-01":1476.3205319946537,"GB2-02":1428.8231781524264,"GB2-03":1363.0584808767833,"GB2-05":945.0674090073451,"GB2-06":1368.9098744914804,"GB2-07":1101.7822101593483,"GB2-08":1547.4996393916958}},"per_game_tracks":{"medium":{"GB2-01":12.579978838993426,"GB2-02":10.746700809550001,"GB2-04":29.558055123630105,"GB2-05":48.43969869217212,"GB2-06":57.82115624580523,"GB2-07":32.29308716542273,"GB2-08":40.44050248293845},"none":{"GB2-01":41.94845904405925,"GB2-02":10.4996181061563,"GB2-03":24.184427349708432,"GB2-05":14.160401525981356,"GB2-06":42.52477509866081,"GB2-07":20.33044730875999,"GB2-08":41.53835062072972}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":30.8268415765198,"none":25.948783691247797},"reasoning_agg":{"medium":{"max":57.82115624580523,"mean":30.8268415765198,"min":10.746700809550001},"none":{"max":42.52477509866081,"mean":25.948783691247797,"min":10.4996181061563}},"reasoning_labels":{"highest":"Setting not tested","medium":"Medium","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":57.82115624580523,"reasoning_variance":4.878057885272003},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":57.82115624580523,"expected_score":33.67312746490716,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.84628588838736},"none":{"ceiling_score":42.52477509866081,"expected_score":29.284060162205115,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.335276470957318}}},{"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":0.09094043001999999},"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":0.16008749804000003},"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":28.862324007756367,"highest":30.445418797781553,"medium":27.778620882094394,"none":28.2443395218878},"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":"2026-09-25T14:26:54Z","match_totals_all":{"draws":2851,"losses":3679,"wins":2123},"match_totals_tracks":{"highest":{"draws":707,"losses":696,"wins":427},"medium":{"draws":1596,"losses":2118,"wins":1209},"none":{"draws":548,"losses":865,"wins":487}},"model_slug":"deepseek-deepseek-v4-flash","overall":{"max":79.88316261692358,"mean":27.87648918191451,"min":9.347070314016047},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":51,"overall_ranking_status":"ranked","per_game":{"GB2-01":18.807057281000937,"GB2-02":14.424491371108513,"GB2-03":21.86788153475712,"GB2-04":13.08582389461898,"GB2-06":79.88316261692358,"GB2-07":40.43117903521025,"GB2-08":24.618335850851498},"per_game_all":{"GB2-01":26.38755198516021,"GB2-02":11.601312257045882,"GB2-03":23.646708876301023,"GB2-06":56.84102102226644,"GB2-07":30.692122140932373,"GB2-08":24.005227764832245},"per_game_match_totals_all":{"GB2-01":{"draws":202,"losses":658,"wins":244},"GB2-02":{"draws":978,"losses":174,"wins":26},"GB2-03":{"draws":352,"losses":293,"wins":168},"GB2-04":{"draws":521,"losses":203,"wins":68},"GB2-05":{"draws":0,"losses":520,"wins":406},"GB2-06":{"draws":37,"losses":652,"wins":625},"GB2-07":{"draws":0,"losses":811,"wins":445},"GB2-08":{"draws":761,"losses":368,"wins":141}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":62,"losses":152,"wins":8},"GB2-02":{"draws":180,"losses":25,"wins":15},"GB2-03":{"draws":103,"losses":93,"wins":40},"GB2-04":{"draws":162,"losses":93,"wins":41},"GB2-06":{"draws":19,"losses":45,"wins":172},"GB2-07":{"draws":0,"losses":205,"wins":133},"GB2-08":{"draws":181,"losses":83,"wins":18}},"medium":{"GB2-01":{"draws":77,"losses":353,"wins":212},"GB2-02":{"draws":550,"losses":88,"wins":8},"GB2-03":{"draws":156,"losses":103,"wins":82},"GB2-04":{"draws":359,"losses":110,"wins":27},"GB2-05":{"draws":0,"losses":413,"wins":261},"GB2-06":{"draws":7,"losses":470,"wins":265},"GB2-07":{"draws":0,"losses":402,"wins":258},"GB2-08":{"draws":447,"losses":179,"wins":96}},"none":{"GB2-01":{"draws":63,"losses":153,"wins":24},"GB2-02":{"draws":248,"losses":61,"wins":3},"GB2-03":{"draws":93,"losses":97,"wins":46},"GB2-05":{"draws":0,"losses":107,"wins":145},"GB2-06":{"draws":11,"losses":137,"wins":188},"GB2-07":{"draws":0,"losses":204,"wins":54},"GB2-08":{"draws":133,"losses":106,"wins":27}}},"per_game_raw_elo_all":{"GB2-01":1256.0780705086233,"GB2-02":1435.62891834996,"GB2-03":1353.1625560449904,"GB2-06":1602.6863398820362,"GB2-07":1255.8010863765448,"GB2-08":1315.567319043038},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1150.6627242367563,"GB2-02":1457.0772478703082,"GB2-03":1332.266627525364,"GB2-04":1410.714716134723,"GB2-06":1985.940688516747,"GB2-07":1398.4683915813177,"GB2-08":1322.8531658008642},"medium":{"GB2-01":1394.4241530668423,"GB2-02":1421.1169514798858,"GB2-03":1389.1241360082765,"GB2-04":1413.158037374963,"GB2-05":1314.5396769568247,"GB2-06":1234.6135842573058,"GB2-07":1287.0720177178437,"GB2-08":1422.528673146514},"none":{"GB2-01":1223.1473342222712,"GB2-02":1428.692555699686,"GB2-03":1338.0969046013313,"GB2-05":1507.4080298081694,"GB2-06":1587.5047468720559,"GB2-07":1081.8628498304731,"GB2-08":1201.3201181817356}},"per_game_tracks":{"highest":{"GB2-01":18.807057281000937,"GB2-02":14.424491371108513,"GB2-03":21.86788153475712,"GB2-04":13.08582389461898,"GB2-06":79.88316261692358,"GB2-07":40.43117903521025,"GB2-08":24.618335850851498},"medium":{"GB2-01":36.27867614801619,"GB2-02":9.347070314016047,"GB2-03":26.65635682627981,"GB2-04":13.10783027783285,"GB2-05":37.56680586128569,"GB2-06":34.56862070317807,"GB2-07":32.643306070184295,"GB2-08":32.06030085596221},"none":{"GB2-01":24.0769225264635,"GB2-02":11.032375086013085,"GB2-03":22.41588826786613,"GB2-05":49.77498312108857,"GB2-06":56.07127974669768,"GB2-07":19.001881317402578,"GB2-08":15.337046587683027}},"provider_color":"#4C8BF5","provider_company":"DeepSeek","provider_key":"deepseek","provider_text_color":"#f6f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":29.44584120542539,"medium":26.8665990385216,"none":27.31702730179655},"reasoning_agg":{"highest":{"max":79.88316261692358,"mean":29.44584120542539,"min":13.08582389461898},"medium":{"max":37.56680586128569,"mean":26.8665990385216,"min":9.347070314016047},"none":{"max":56.07127974669768,"mean":27.31702730179655,"min":11.032375086013085}},"reasoning_labels":{"highest":"XHigh","medium":"High","none":"Reasoning disabled"},"reasoning_settings":{"balanced":"high","baseline":"none","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":79.88316261692358,"expected_score":24.627452192736428,"reasoning_variance":2.5792421669037893,"reliability_score":99.92013221077734,"uncertainty_avg":0.07986778922265798,"uncertainty_penalty":-3.2490369891780837},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":79.88316261692358,"expected_score":20.71700114771454,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.728840057710848},"medium":{"ceiling_score":37.56680586128569,"expected_score":26.14999659067365,"reliability_score":99.82029747424902,"uncertainty_avg":0.17970252575098045,"uncertainty_penalty":-0.7166024478479507},"none":{"ceiling_score":56.07127974669768,"expected_score":28.826805070762457,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.5097777689659075}}},{"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":0.04917796},"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":0.04917795999999999},"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":26.434769750155958,"none":31.432327599551694},"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":"2026-09-25T16:02:53Z","match_totals_all":{"draws":2911,"losses":3045,"wins":1653},"match_totals_tracks":{"medium":{"draws":1976,"losses":1838,"wins":793},"none":{"draws":935,"losses":1207,"wins":860}},"model_slug":"poolside-laguna-s-2-1","overall":{"max":46.950499952815655,"mean":27.566070032428385,"min":6.704785781203059},"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":165,"losses":415,"wins":336},"GB2-02":{"draws":942,"losses":117,"wins":13},"GB2-03":{"draws":547,"losses":557,"wins":304},"GB2-04":{"draws":238,"losses":110,"wins":36},"GB2-05":{"draws":0,"losses":736,"wins":507},"GB2-06":{"draws":21,"losses":464,"wins":179},"GB2-07":{"draws":0,"losses":276,"wins":222},"GB2-08":{"draws":998,"losses":370,"wins":56}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":72,"losses":230,"wins":162},"GB2-02":{"draws":721,"losses":91,"wins":2},"GB2-03":{"draws":315,"losses":333,"wins":168},"GB2-04":{"draws":238,"losses":110,"wins":36},"GB2-05":{"draws":0,"losses":543,"wins":282},"GB2-06":{"draws":14,"losses":302,"wins":106},"GB2-08":{"draws":616,"losses":229,"wins":37}},"none":{"GB2-01":{"draws":93,"losses":185,"wins":174},"GB2-02":{"draws":221,"losses":26,"wins":11},"GB2-03":{"draws":232,"losses":224,"wins":136},"GB2-05":{"draws":0,"losses":193,"wins":225},"GB2-06":{"draws":7,"losses":162,"wins":73},"GB2-07":{"draws":0,"losses":276,"wins":222},"GB2-08":{"draws":382,"losses":141,"wins":19}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1423.705955614129,"GB2-02":1467.251491718369,"GB2-03":1404.2676204995091,"GB2-04":1365.6162527706854,"GB2-05":1325.7183885846332,"GB2-06":1144.6544348969242,"GB2-08":1325.1732080243237},"none":{"GB2-01":1493.1664104314107,"GB2-02":1427.8164920623371,"GB2-03":1348.950691072303,"GB2-05":1465.02865773044,"GB2-06":1136.8956765035823,"GB2-07":1446.8511196698983,"GB2-08":1309.5085507135805}},"per_game_tracks":{"medium":{"GB2-01":38.973297355450676,"GB2-02":16.857571915656177,"GB2-03":29.209728963258087,"GB2-04":6.704785781203059,"GB2-05":38.67815533375288,"GB2-06":29.464909991973933,"GB2-08":25.154938909796876},"none":{"GB2-01":43.374154056993305,"GB2-02":10.592781159581312,"GB2-03":23.486121890739962,"GB2-05":46.950499952815655,"GB2-06":28.621128644913895,"GB2-07":43.43267997067568,"GB2-08":23.568927521142058}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":24.88809720804685,"none":30.244042856809923},"reasoning_agg":{"medium":{"max":38.973297355450676,"mean":24.88809720804685,"min":6.704785781203059},"none":{"max":46.950499952815655,"mean":30.244042856809923,"min":10.592781159581312}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":46.950499952815655,"reasoning_variance":5.355945648763072},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":38.973297355450676,"expected_score":23.62386520152192,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.2642320065249315},"none":{"ceiling_score":46.950499952815655,"expected_score":31.962915195030465,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.7188723382205424}}},{"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":0.010139173999999999}},"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":0.010139173999999999},"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":0.041725613},"codegen_latency_ms":{"attempt_count":25,"max_ms":368409,"mean_ms":82415.5294117647,"min_ms":16892,"run_count":17},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":14,"max_ms":368409,"mean_ms":127998.11111111111,"min_ms":27775,"run_count":9},"none":{"attempt_count":11,"max_ms":46063,"mean_ms":31135.125,"min_ms":16892,"run_count":8}},"codegen_output_tokens":{"attempt_count":25,"output_max":27553,"output_mean":7690.823529411765,"output_min":1430,"run_count":17},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":14,"output_max":27553,"output_mean":12332.666666666666,"output_min":2974,"run_count":9},"none":{"attempt_count":11,"output_max":3514,"output_mean":2468.75,"output_min":1430,"run_count":8}},"display_name":"Hy3 Preview","economics":{"highest":32.87777735942499,"none":25.065186174186948},"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":"2026-09-25T04:44:49Z","match_totals_all":{"draws":1062,"losses":1072,"wins":752},"match_totals_tracks":{"highest":{"draws":464,"losses":612,"wins":450},"none":{"draws":598,"losses":460,"wins":302}},"model_slug":"tencent-hy3-preview","overall":{"max":61.8142594407856,"mean":27.100724973200947,"min":3.2968970313112287},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_bracket_scores","untested_or_ineligible_settings","missing_generation_quality"],"overall_official_rank":53,"overall_ranking_status":"partial","per_game":{"GB2-01":57.3097596033617,"GB2-02":7.416920025051943,"GB2-04":11.384109348575187,"GB2-05":61.8142594407856,"GB2-06":28.190333048264026,"GB2-07":30.740095434691877,"GB2-08":33.2889646152446},"per_game_match_totals_all":{"GB2-01":{"draws":67,"losses":96,"wins":235},"GB2-02":{"draws":335,"losses":73,"wins":2},"GB2-03":{"draws":62,"losses":100,"wins":42},"GB2-04":{"draws":313,"losses":77,"wins":50},"GB2-05":{"draws":0,"losses":245,"wins":183},"GB2-06":{"draws":0,"losses":157,"wins":49},"GB2-07":{"draws":0,"losses":161,"wins":89},"GB2-08":{"draws":285,"losses":163,"wins":102}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":35,"losses":60,"wins":103},"GB2-02":{"draws":165,"losses":33,"wins":2},"GB2-04":{"draws":184,"losses":48,"wins":8},"GB2-05":{"draws":0,"losses":62,"wins":110},"GB2-06":{"draws":0,"losses":157,"wins":49},"GB2-07":{"draws":0,"losses":161,"wins":89},"GB2-08":{"draws":80,"losses":91,"wins":89}},"none":{"GB2-01":{"draws":32,"losses":36,"wins":132},"GB2-02":{"draws":170,"losses":40,"wins":0},"GB2-03":{"draws":62,"losses":100,"wins":42},"GB2-04":{"draws":129,"losses":29,"wins":42},"GB2-05":{"draws":0,"losses":183,"wins":73},"GB2-08":{"draws":205,"losses":72,"wins":13}}},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1689.2694783053653,"GB2-02":1408.6240175501182,"GB2-04":1401.9968696972862,"GB2-05":1703.8573282748,"GB2-06":1131.9050992310254,"GB2-07":1257.3955730790376,"GB2-08":1438.0276962334312},"none":{"GB2-01":1695.1065782809987,"GB2-02":1378.6914103410684,"GB2-03":1291.6821137938018,"GB2-04":1458.3635699825543,"GB2-05":1099.7712464212616,"GB2-08":1365.0274390867012}},"per_game_tracks":{"highest":{"GB2-01":57.3097596033617,"GB2-02":7.416920025051943,"GB2-04":11.384109348575187,"GB2-05":61.8142594407856,"GB2-06":28.190333048264026,"GB2-07":30.740095434691877,"GB2-08":33.2889646152446},"none":{"GB2-01":57.73838761870533,"GB2-02":3.2968970313112287,"GB2-03":17.86950861804385,"GB2-04":19.522920844339357,"GB2-05":24.117792770251928,"GB2-08":27.84561016247001}},"provider_color":"#12B7F5","provider_company":"Tencent","provider_key":"tencent","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":30.875665898404755,"none":23.325784047997143},"reasoning_agg":{"highest":{"max":61.8142594407856,"mean":30.875665898404755,"min":7.416920025051943},"none":{"max":57.73838761870533,"mean":23.325784047997143,"min":3.2968970313112287}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":61.8142594407856,"reasoning_variance":7.549881850407612},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":61.8142594407856,"expected_score":24.13763643259788,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.738029465806875},"none":{"ceiling_score":57.73838761870533,"expected_score":25.80164176828504,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.475857720287898}}},{"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":0.6081093000000001},"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":0.6081093},"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":0.9722945000000001}},"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":1.8519748999999996},"codegen_latency_ms":{"attempt_count":132,"max_ms":115030,"mean_ms":50137.9375,"min_ms":13430,"run_count":48},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":50,"max_ms":115030,"mean_ms":74972.3125,"min_ms":38302,"run_count":16},"medium":{"attempt_count":48,"max_ms":75176,"mean_ms":48761.1875,"min_ms":19840,"run_count":16},"none":{"attempt_count":34,"max_ms":54024,"mean_ms":26680.3125,"min_ms":13430,"run_count":16}},"codegen_output_tokens":{"attempt_count":132,"output_max":33866,"output_mean":12598.979166666666,"output_min":1476,"run_count":48},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":50,"output_max":33866,"output_mean":21067.4375,"output_min":11641,"run_count":16},"medium":{"attempt_count":48,"output_max":19346,"output_mean":12054.5625,"output_min":4066,"run_count":16},"none":{"attempt_count":34,"output_max":9270,"output_mean":4674.9375,"output_min":1476,"run_count":16}},"display_name":"Gemini 3.5 Flash Lite","economics":{"all":27.7950199744936,"highest":29.825390658770534,"medium":22.738090266039418,"none":30.82157899867084},"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":"2026-09-25T16:20:00Z","match_totals_all":{"draws":5137,"losses":7555,"wins":4209},"match_totals_tracks":{"highest":{"draws":1284,"losses":2294,"wins":1486},"medium":{"draws":1872,"losses":2656,"wins":940},"none":{"draws":1981,"losses":2605,"wins":1783}},"model_slug":"google-gemini-3-5-flash-lite","overall":{"max":56.66854839969095,"mean":27.055334108396753,"min":8.198390781857146},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":54,"overall_ranking_status":"ranked","per_game":{"GB2-01":40.24576283638427,"GB2-02":13.016216434051367,"GB2-03":33.923231532018065,"GB2-04":14.956475308723242,"GB2-05":25.026580421066036,"GB2-06":45.48522862689852,"GB2-07":42.77503608244635,"GB2-08":23.17459402857645},"per_game_all":{"GB2-01":38.26280859174692,"GB2-02":11.258007153856923,"GB2-03":29.394373531484735,"GB2-04":18.497952733784853,"GB2-05":20.242706703812807,"GB2-06":39.098636367751546,"GB2-07":41.77558521698756,"GB2-08":23.830089496523446},"per_game_match_totals_all":{"GB2-01":{"draws":408,"losses":1082,"wins":702},"GB2-02":{"draws":1229,"losses":172,"wins":34},"GB2-03":{"draws":579,"losses":725,"wins":600},"GB2-04":{"draws":1412,"losses":481,"wins":296},"GB2-05":{"draws":0,"losses":1905,"wins":431},"GB2-06":{"draws":55,"losses":1498,"wins":991},"GB2-07":{"draws":0,"losses":1115,"wins":1068},"GB2-08":{"draws":1454,"losses":577,"wins":87}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":83,"losses":184,"wins":101},"GB2-02":{"draws":271,"losses":51,"wins":30},"GB2-03":{"draws":167,"losses":296,"wins":287},"GB2-04":{"draws":460,"losses":169,"wins":82},"GB2-05":{"draws":0,"losses":568,"wins":182},"GB2-06":{"draws":35,"losses":429,"wins":356},"GB2-07":{"draws":0,"losses":474,"wins":431},"GB2-08":{"draws":268,"losses":123,"wins":17}},"medium":{"GB2-01":{"draws":157,"losses":470,"wins":331},"GB2-02":{"draws":361,"losses":47,"wins":1},"GB2-03":{"draws":301,"losses":254,"wins":145},"GB2-04":{"draws":458,"losses":94,"wins":53},"GB2-05":{"draws":0,"losses":623,"wins":145},"GB2-06":{"draws":9,"losses":659,"wins":122},"GB2-07":{"draws":0,"losses":298,"wins":106},"GB2-08":{"draws":586,"losses":211,"wins":37}},"none":{"GB2-01":{"draws":168,"losses":428,"wins":270},"GB2-02":{"draws":597,"losses":74,"wins":3},"GB2-03":{"draws":111,"losses":175,"wins":168},"GB2-04":{"draws":494,"losses":218,"wins":161},"GB2-05":{"draws":0,"losses":714,"wins":104},"GB2-06":{"draws":11,"losses":410,"wins":513},"GB2-07":{"draws":0,"losses":343,"wins":531},"GB2-08":{"draws":600,"losses":243,"wins":33}}},"per_game_raw_elo_all":{"GB2-01":1414.6951118860488,"GB2-02":1428.619865989195,"GB2-03":1406.6201646345346,"GB2-04":1444.5427553005954,"GB2-05":1033.5440183099136,"GB2-06":1304.171459636411,"GB2-07":1416.1081677646644,"GB2-08":1308.1791469539821},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1443.7279758888242,"GB2-02":1441.4601523846961,"GB2-03":1455.2227097154012,"GB2-04":1421.0892976785772,"GB2-05":1109.881419184016,"GB2-06":1410.2480292126502,"GB2-07":1430.5367015067034,"GB2-08":1299.8401973546747},"medium":{"GB2-01":1418.1572038478112,"GB2-02":1436.6811806382134,"GB2-03":1346.9246507141288,"GB2-04":1442.018220570183,"GB2-05":1059.0605185213187,"GB2-06":943.9992522361157,"GB2-07":1179.55633657311,"GB2-08":1313.516631196398},"none":{"GB2-01":1382.2001559215114,"GB2-02":1407.7182649446754,"GB2-03":1417.7131334740745,"GB2-04":1470.5207476530259,"GB2-05":931.6901172244059,"GB2-06":1558.267097460467,"GB2-07":1638.2314652141795,"GB2-08":1311.1806123108736}},"per_game_tracks":{"highest":{"GB2-01":40.24576283638427,"GB2-02":13.016216434051367,"GB2-03":33.923231532018065,"GB2-04":14.956475308723242,"GB2-05":25.026580421066036,"GB2-06":45.48522862689852,"GB2-07":42.77503608244635,"GB2-08":23.17459402857645},"medium":{"GB2-01":38.59409823246796,"GB2-02":12.559414245662259,"GB2-03":23.680993596380297,"GB2-04":17.810416612074924,"GB2-05":21.841650392139822,"GB2-06":17.306065189421517,"GB2-07":25.883171168825367,"GB2-08":24.228912691343204},"none":{"GB2-01":35.948564706388524,"GB2-02":8.198390781857146,"GB2-03":30.57889546605584,"GB2-04":22.726966280556393,"GB2-05":13.859889298232568,"GB2-06":54.50461528693461,"GB2-07":56.66854839969095,"GB2-08":24.086761769650685}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":28.84616969998549,"medium":21.99155806446691,"none":30.32827456073786},"reasoning_agg":{"highest":{"max":45.48522862689852,"mean":28.84616969998549,"min":13.016216434051367},"medium":{"max":38.59409823246796,"mean":21.99155806446691,"min":12.559414245662259},"none":{"max":56.66854839969095,"mean":30.32827456073786,"min":8.198390781857146}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Minimal"},"reasoning_settings":{"balanced":"medium","baseline":"minimal","intensive":"high"},"score_diagnostics":{"ceiling_score":56.66854839969095,"expected_score":22.995521191714076,"reasoning_variance":8.336716496270949,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.059812916682677},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":45.48522862689852,"expected_score":18.95227672354238,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.893892976443112},"medium":{"ceiling_score":38.59409823246796,"expected_score":19.150544803357874,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.841013261109037},"none":{"ceiling_score":56.66854839969095,"expected_score":30.883742048241977,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.5554674875041172}}},{"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":0.08145696000000001}},"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":0.43500895999999994},"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":0.08145696000000001}},"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":0.51646592},"codegen_latency_ms":{"attempt_count":29,"max_ms":1361767,"mean_ms":422352.64705882355,"min_ms":51720,"run_count":17},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":16,"max_ms":1361767,"mean_ms":800306.75,"min_ms":68429,"run_count":8},"none":{"attempt_count":13,"max_ms":153912,"mean_ms":86393.44444444444,"min_ms":51720,"run_count":9}},"codegen_output_tokens":{"attempt_count":29,"output_max":62955,"output_mean":20190.70588235294,"output_min":2265,"run_count":17},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":16,"output_max":62955,"output_mean":38265.375,"output_min":3140,"run_count":8},"none":{"attempt_count":13,"output_max":7814,"output_mean":4124.333333333333,"output_min":2265,"run_count":9}},"display_name":"Qwen3.7 Plus","economics":{"medium":38.20400839484258,"none":20.17038574595111},"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":"2026-09-25T15:25:52Z","match_totals_all":{"draws":902,"losses":1126,"wins":679},"match_totals_tracks":{"medium":{"draws":466,"losses":482,"wins":458},"none":{"draws":436,"losses":644,"wins":221}},"model_slug":"qwen-qwen3-7-plus","overall":{"max":71.62538316070135,"mean":26.88941841152139,"min":9.261021826492382},"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":89,"losses":198,"wins":99},"GB2-02":{"draws":411,"losses":31,"wins":6},"GB2-04":{"draws":170,"losses":24,"wins":17},"GB2-05":{"draws":0,"losses":211,"wins":211},"GB2-06":{"draws":7,"losses":224,"wins":217},"GB2-07":{"draws":0,"losses":385,"wins":129},"GB2-08":{"draws":225,"losses":53,"wins":0}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":42,"losses":80,"wins":70},"GB2-02":{"draws":195,"losses":13,"wins":6},"GB2-05":{"draws":0,"losses":103,"wins":121},"GB2-06":{"draws":4,"losses":50,"wins":170},"GB2-07":{"draws":0,"losses":183,"wins":91},"GB2-08":{"draws":225,"losses":53,"wins":0}},"none":{"GB2-01":{"draws":47,"losses":118,"wins":29},"GB2-02":{"draws":216,"losses":18,"wins":0},"GB2-04":{"draws":170,"losses":24,"wins":17},"GB2-05":{"draws":0,"losses":108,"wins":90},"GB2-06":{"draws":3,"losses":174,"wins":47},"GB2-07":{"draws":0,"losses":202,"wins":38}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1489.5348404139154,"GB2-02":1432.9764402657258,"GB2-05":1601.7502453944767,"GB2-06":1849.9042563122262,"GB2-07":1153.9213565009122,"GB2-08":1317.0055779922611},"none":{"GB2-01":1164.2895404365493,"GB2-02":1419.5981193259827,"GB2-04":1438.1114181328019,"GB2-05":1411.7681750856045,"GB2-06":983.0303224250979,"GB2-07":988.9738841198142}},"per_game_tracks":{"medium":{"GB2-01":42.95850131307906,"GB2-02":10.977938094235043,"GB2-05":55.62022193946525,"GB2-06":71.62538316070135,"GB2-07":23.88057228629806,"GB2-08":24.161433575276742},"none":{"GB2-01":19.65077416582446,"GB2-02":9.261021826492382,"GB2-04":16.577922253499185,"GB2-05":43.55040400948236,"GB2-06":19.267003258236837,"GB2-07":12.715188962171446}},"provider_color":"#FF6A00","provider_company":"Alibaba","provider_key":"qwen","provider_text_color":"#fff8f2","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":35.55283584941791,"none":18.226000973624874},"reasoning_agg":{"medium":{"max":71.62538316070135,"mean":35.55283584941791,"min":10.977938094235043},"none":{"max":43.55040400948236,"mean":18.226000973624874,"min":9.261021826492382}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":71.62538316070135,"reasoning_variance":17.326834875793036},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":71.62538316070135,"expected_score":39.30932872197307,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.7564928725551567},"none":{"ceiling_score":43.55040400948236,"expected_score":18.66912573071505,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.4431247570901746}}},{"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":0.48528460000000007}},"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":0.4852846000000001}},"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":0.48528460000000007},"codegen_latency_ms":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":357442,"mean_ms":205939.25,"min_ms":129630,"run_count":8}},"codegen_output_tokens":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":29845,"output_mean":22432.25,"output_min":16334,"run_count":8}},"display_name":"Grok Build 0.1","economics":{"medium":26.302156667515924},"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":"2026-09-25T13:41:32Z","match_totals_all":{"draws":706,"losses":739,"wins":429},"match_totals_tracks":{"medium":{"draws":706,"losses":739,"wins":429}},"model_slug":"x-ai-grok-build-0-1","overall":{"max":50.969829451519225,"mean":26.302156667515924,"min":12.067201319254902},"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":46,"losses":93,"wins":73},"GB2-02":{"draws":220,"losses":34,"wins":6},"GB2-03":{"draws":56,"losses":65,"wins":31},"GB2-04":{"draws":194,"losses":32,"wins":10},"GB2-05":{"draws":0,"losses":93,"wins":135},"GB2-06":{"draws":0,"losses":150,"wins":106},"GB2-07":{"draws":0,"losses":205,"wins":57},"GB2-08":{"draws":190,"losses":67,"wins":11}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":46,"losses":93,"wins":73},"GB2-02":{"draws":220,"losses":34,"wins":6},"GB2-03":{"draws":56,"losses":65,"wins":31},"GB2-04":{"draws":194,"losses":32,"wins":10},"GB2-05":{"draws":0,"losses":93,"wins":135},"GB2-06":{"draws":0,"losses":150,"wins":106},"GB2-07":{"draws":0,"losses":205,"wins":57},"GB2-08":{"draws":190,"losses":67,"wins":11}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1351.8380320982249,"GB2-02":1438.1908067528893,"GB2-03":1290.242440849019,"GB2-04":1434.5652326310567,"GB2-05":1527.6673413728931,"GB2-06":1375.862610827383,"GB2-07":994.9203420266373,"GB2-08":1319.5573778937342}},"per_game_tracks":{"medium":{"GB2-01":33.18568291274274,"GB2-02":12.067201319254902,"GB2-03":17.32053682080132,"GB2-04":16.267449298158713,"GB2-05":50.969829451519225,"GB2-06":43.09731404389463,"GB2-07":13.187537598700027,"GB2-08":24.3217018950558}},"provider_color":"#9CA3AF","provider_company":"xAI","provider_key":"x-ai","provider_text_color":"#0b1120","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.302156667515924},"reasoning_agg":{"medium":{"max":50.969829451519225,"mean":26.302156667515924,"min":12.067201319254902}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Setting not tested"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":50.969829451519225},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":50.969829451519225,"expected_score":24.55651727531458,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.745639392201344}}},{"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":0.214047204}},"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":1.3863592560000002},"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":0.214047204}},"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":1.60040646},"codegen_latency_ms":{"attempt_count":87,"max_ms":1635062,"mean_ms":598630.75,"min_ms":47979,"run_count":32},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":49,"max_ms":1635062,"mean_ms":1021590.9375,"min_ms":525940,"run_count":16},"none":{"attempt_count":38,"max_ms":457140,"mean_ms":175670.5625,"min_ms":47979,"run_count":16}},"codegen_output_tokens":{"attempt_count":97,"output_max":110598,"output_mean":38325.9375,"output_min":2150,"run_count":32},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":59,"output_max":110598,"output_mean":68392.8125,"output_min":16796,"run_count":16},"none":{"attempt_count":38,"output_max":22812,"output_mean":8259.0625,"output_min":2150,"run_count":16}},"display_name":"LongCat 2.0","economics":{"medium":26.99763459419179,"none":26.51917609731877},"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":"2026-09-25T15:14:18Z","match_totals_all":{"draws":2289,"losses":3709,"wins":1948},"match_totals_tracks":{"medium":{"draws":1249,"losses":2341,"wins":1177},"none":{"draws":1040,"losses":1368,"wins":771}},"model_slug":"meituan-longcat-2-0","overall":{"max":41.60041525625513,"mean":25.386317008942793,"min":7.685379769827811},"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":177,"wins":144},"GB2-02":{"draws":535,"losses":71,"wins":2},"GB2-03":{"draws":286,"losses":243,"wins":152},"GB2-04":{"draws":536,"losses":268,"wins":110},"GB2-05":{"draws":0,"losses":830,"wins":412},"GB2-06":{"draws":83,"losses":799,"wins":414},"GB2-07":{"draws":0,"losses":826,"wins":534},"GB2-08":{"draws":692,"losses":495,"wins":180}},"per_game_match_totals_tracks":{"medium":{"GB2-02":{"draws":320,"losses":44,"wins":2},"GB2-03":{"draws":165,"losses":125,"wins":87},"GB2-04":{"draws":418,"losses":221,"wins":66},"GB2-05":{"draws":0,"losses":503,"wins":325},"GB2-06":{"draws":47,"losses":541,"wins":222},"GB2-07":{"draws":0,"losses":525,"wins":321},"GB2-08":{"draws":299,"losses":382,"wins":154}},"none":{"GB2-01":{"draws":157,"losses":177,"wins":144},"GB2-02":{"draws":215,"losses":27,"wins":0},"GB2-03":{"draws":121,"losses":118,"wins":65},"GB2-04":{"draws":118,"losses":47,"wins":44},"GB2-05":{"draws":0,"losses":327,"wins":87},"GB2-06":{"draws":36,"losses":258,"wins":192},"GB2-07":{"draws":0,"losses":301,"wins":213},"GB2-08":{"draws":393,"losses":113,"wins":26}}},"per_game_raw_elo_tracks":{"medium":{"GB2-02":1431.3376250866384,"GB2-03":1409.2127966123949,"GB2-04":1423.459024040264,"GB2-05":1297.5060696205567,"GB2-06":1191.8149950533534,"GB2-07":1330.7340905811943,"GB2-08":1352.5170691998403},"none":{"GB2-01":1409.5992831781336,"GB2-02":1407.9765137394702,"GB2-03":1378.1594077190425,"GB2-04":1495.2986589973464,"GB2-05":989.1863512819759,"GB2-06":1351.7431065972619,"GB2-07":1296.3619056884113,"GB2-08":1319.3611201675367}},"per_game_tracks":{"medium":{"GB2-02":11.64843348541389,"GB2-03":29.60871326724313,"GB2-04":15.298717008537093,"GB2-05":36.90268984079009,"GB2-06":32.2888894086943,"GB2-07":36.04461312474943,"GB2-08":27.191386023914582},"none":{"GB2-01":37.44066886204282,"GB2-02":7.685379769827811,"GB2-03":25.58413890549305,"GB2-04":25.19033659038525,"GB2-05":16.978770000497704,"GB2-06":41.60041525625513,"GB2-07":33.37480073077782,"GB2-08":24.298898663270595}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":25.12412993761782,"none":25.648504080267767},"reasoning_agg":{"medium":{"max":36.90268984079009,"mean":25.12412993761782,"min":11.64843348541389},"none":{"max":41.60041525625513,"mean":25.648504080267767,"min":7.685379769827811}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{"balanced":"enabled","baseline":"none"},"score_diagnostics":{"ceiling_score":41.60041525625513,"reasoning_variance":0.5243741426499469},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":36.90268984079009,"expected_score":24.928384357529982,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.19574558008783782},"none":{"ceiling_score":41.60041525625513,"expected_score":26.83926627456163,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.190762194293864}}},{"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":0.05953976200000001},"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":0.009085673},"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":0.009855891},"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":0.059539761999999996}},"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":25.040676780953035,"highest":27.683808602948602,"medium":23.257439814922698,"none":26.57466175163876},"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":"2026-09-25T16:16:30Z","match_totals_all":{"draws":1913,"losses":2334,"wins":1086},"match_totals_tracks":{"highest":{"draws":640,"losses":694,"wins":403},"medium":{"draws":742,"losses":953,"wins":361},"none":{"draws":531,"losses":687,"wins":322}},"model_slug":"openai-gpt-oss-120b","overall":{"max":54.825621514346786,"mean":24.920949595397968,"min":5.952533319730318},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":58,"overall_ranking_status":"ranked","per_game":{"GB2-02":13.144887580099901,"GB2-03":30.416960415799508,"GB2-04":14.904812286411738,"GB2-05":54.825621514346786,"GB2-06":26.151419561181175,"GB2-07":35.08448523875982,"GB2-08":19.258473624041308},"per_game_all":{"GB2-02":11.607124031823638,"GB2-03":27.787622460564844,"GB2-05":33.02355400675667,"GB2-07":31.193386452497066,"GB2-08":21.59169695312296},"per_game_match_totals_all":{"GB2-01":{"draws":93,"losses":287,"wins":198},"GB2-02":{"draws":622,"losses":69,"wins":9},"GB2-03":{"draws":261,"losses":263,"wins":179},"GB2-04":{"draws":361,"losses":138,"wins":51},"GB2-05":{"draws":0,"losses":501,"wins":219},"GB2-06":{"draws":3,"losses":331,"wins":146},"GB2-07":{"draws":0,"losses":511,"wins":263},"GB2-08":{"draws":573,"losses":234,"wins":21}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":196,"losses":37,"wins":7},"GB2-03":{"draws":94,"losses":75,"wins":68},"GB2-04":{"draws":158,"losses":42,"wins":34},"GB2-05":{"draws":0,"losses":123,"wins":123},"GB2-06":{"draws":0,"losses":180,"wins":64},"GB2-07":{"draws":0,"losses":148,"wins":104},"GB2-08":{"draws":192,"losses":89,"wins":3}},"medium":{"GB2-01":{"draws":45,"losses":131,"wins":76},"GB2-02":{"draws":208,"losses":18,"wins":2},"GB2-03":{"draws":96,"losses":88,"wins":52},"GB2-04":{"draws":203,"losses":96,"wins":17},"GB2-05":{"draws":0,"losses":199,"wins":47},"GB2-06":{"draws":3,"losses":151,"wins":82},"GB2-07":{"draws":0,"losses":193,"wins":69},"GB2-08":{"draws":187,"losses":77,"wins":16}},"none":{"GB2-01":{"draws":48,"losses":156,"wins":122},"GB2-02":{"draws":218,"losses":14,"wins":0},"GB2-03":{"draws":71,"losses":100,"wins":59},"GB2-05":{"draws":0,"losses":179,"wins":49},"GB2-07":{"draws":0,"losses":170,"wins":90},"GB2-08":{"draws":194,"losses":68,"wins":2}}},"per_game_raw_elo_all":{"GB2-02":1436.2990870640244,"GB2-03":1395.3406566717506,"GB2-05":1242.023362481359,"GB2-07":1263.76852107672,"GB2-08":1283.2572103775562},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1446.8502480309085,"GB2-03":1423.1661562967663,"GB2-04":1425.6481745285778,"GB2-05":1587.9165865736045,"GB2-06":1095.9008746850254,"GB2-07":1322.1159437249746,"GB2-08":1252.1798924471577},"medium":{"GB2-01":1345.5935344813565,"GB2-02":1438.1856422429778,"GB2-03":1351.1217167129957,"GB2-04":1362.7129756772986,"GB2-05":1080.1171427813263,"GB2-06":1301.558641338468,"GB2-07":1168.020631803829,"GB2-08":1335.223467236304},"none":{"GB2-01":1514.518874276408,"GB2-02":1423.8613709181875,"GB2-03":1411.73409700549,"GB2-05":1058.036358089146,"GB2-07":1301.1689877013564,"GB2-08":1262.3682714492068}},"per_game_tracks":{"highest":{"GB2-02":13.144887580099901,"GB2-03":30.416960415799508,"GB2-04":14.904812286411738,"GB2-05":54.825621514346786,"GB2-06":26.151419561181175,"GB2-07":35.08448523875982,"GB2-08":19.258473624041308},"medium":{"GB2-01":32.899998911953496,"GB2-02":11.830818971683568,"GB2-03":23.640132783464484,"GB2-04":5.952533319730318,"GB2-05":22.848650743910238,"GB2-06":38.54712305704406,"GB2-07":24.78906384912377,"GB2-08":25.55119688247162},"none":{"GB2-01":45.228110399238034,"GB2-02":9.845665543687444,"GB2-03":29.30577418243054,"GB2-05":21.396389762012983,"GB2-07":33.706610269607616,"GB2-08":19.96542035285595}},"provider_color":"#10A37F","provider_company":"OpenAI","provider_key":"openai","provider_text_color":"#f3fffb","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":26.774899616201456,"medium":23.257439814922698,"none":24.730509355069742},"reasoning_agg":{"highest":{"max":54.825621514346786,"mean":26.774899616201456,"min":13.144887580099901},"medium":{"max":38.54712305704406,"mean":23.257439814922698,"min":5.952533319730318},"none":{"max":45.228110399238034,"mean":24.730509355069742,"min":9.845665543687444}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":54.825621514346786,"expected_score":21.33665130353595,"reasoning_variance":3.5174598012787577,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.584298291862016},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":54.825621514346786,"expected_score":16.396883265966768,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.378016350234688},"medium":{"ceiling_score":38.54712305704406,"expected_score":20.972019866104837,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.285419948817861},"none":{"ceiling_score":45.228110399238034,"expected_score":27.75350782017352,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.022998465103779}}},{"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":0.48605810000000005},"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":0.19924718}},"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":0.19924717999999997},"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":0.48605809999999994}},"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":38.144222768247786,"highest":28.20832575549643,"medium":24.810268396923686,"none":33.99334325098176},"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":"2026-09-25T14:08:15Z","match_totals_all":{"draws":936,"losses":1857,"wins":976},"match_totals_tracks":{"highest":{"draws":220,"losses":609,"wins":282},"medium":{"draws":400,"losses":370,"wins":180},"none":{"draws":316,"losses":878,"wins":514}},"model_slug":"stepfun-step-3-7-flash","overall":{"max":48.401795904394994,"mean":24.84296289334341,"min":11.348188198383951},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":59,"overall_ranking_status":"partial","per_game":{"GB2-01":11.850477367246295,"GB2-05":42.50033505424671,"GB2-06":33.73971611252159,"GB2-07":25.25307257035454,"GB2-08":27.69802767311302},"per_game_all":{"GB2-05":43.27378646301347,"GB2-06":33.0146590734821},"per_game_match_totals_all":{"GB2-01":{"draws":15,"losses":139,"wins":18},"GB2-02":{"draws":204,"losses":25,"wins":5},"GB2-04":{"draws":192,"losses":31,"wins":21},"GB2-05":{"draws":0,"losses":443,"wins":359},"GB2-06":{"draws":44,"losses":616,"wins":330},"GB2-07":{"draws":0,"losses":424,"wins":239},"GB2-08":{"draws":481,"losses":179,"wins":4}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":15,"losses":139,"wins":18},"GB2-05":{"draws":0,"losses":93,"wins":103},"GB2-06":{"draws":8,"losses":163,"wins":75},"GB2-07":{"draws":0,"losses":159,"wins":82},"GB2-08":{"draws":197,"losses":55,"wins":4}},"medium":{"GB2-02":{"draws":204,"losses":25,"wins":5},"GB2-04":{"draws":192,"losses":31,"wins":21},"GB2-05":{"draws":0,"losses":117,"wins":105},"GB2-06":{"draws":4,"losses":197,"wins":49}},"none":{"GB2-05":{"draws":0,"losses":233,"wins":151},"GB2-06":{"draws":32,"losses":256,"wins":206},"GB2-07":{"draws":0,"losses":265,"wins":157},"GB2-08":{"draws":284,"losses":124,"wins":0}}},"per_game_raw_elo_all":{"GB2-05":1404.2437586681363,"GB2-06":1206.8699637804018},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1057.2574789116686,"GB2-05":1395.236482821177,"GB2-06":1221.4331847566114,"GB2-07":1175.991779846738,"GB2-08":1364.5866683300496},"medium":{"GB2-02":1434.4189027911261,"GB2-04":1443.6781418918763,"GB2-05":1487.23979240712,"GB2-06":1023.2764363744144},"none":{"GB2-05":1330.2550007761117,"GB2-06":1375.9002702101798,"GB2-07":1270.8962343284793,"GB2-08":1277.7831903055633}},"per_game_tracks":{"highest":{"GB2-01":11.850477367246295,"GB2-05":42.50033505424671,"GB2-06":33.73971611252159,"GB2-07":25.25307257035454,"GB2-08":27.69802767311302},"medium":{"GB2-02":11.348188198383951,"GB2-04":17.707558680335882,"GB2-05":48.401795904394994,"GB2-06":21.783530804579915},"none":{"GB2-05":38.91922843039871,"GB2-06":43.52073030334479,"GB2-07":32.03360459011067,"GB2-08":21.499809680072865}},"provider_color":"#F59E0B","provider_company":"StepFun","provider_key":"stepfun","provider_text_color":"#1f1300","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":25.08114244133497,"medium":20.862865756455648,"none":28.584880482239612},"reasoning_agg":{"highest":{"max":42.50033505424671,"mean":25.08114244133497,"min":11.850477367246295},"medium":{"max":48.401795904394994,"mean":20.862865756455648,"min":11.348188198383951},"none":{"max":43.52073030334479,"mean":28.584880482239612,"min":21.499809680072865}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Low"},"reasoning_settings":{"baseline":"low"},"score_diagnostics":{"ceiling_score":48.401795904394994,"expected_score":31.410156738002907,"reasoning_variance":7.722014725783964,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":6.567193844659496},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":42.50033505424671,"expected_score":15.876615091456477,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.204527349878491},"medium":{"ceiling_score":48.401795904394994,"expected_score":21.746086211577087,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.8832204551214389},"none":{"ceiling_score":43.52073030334479,"expected_score":31.348981353139507,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.7641008708998953}}},{"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":0.15725572000000002},"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":0.05850166}},"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":0.28235539000000004},"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":26.890185679313266,"highest":31.350170089323683,"medium":21.350513794117806,"none":23.31994578837838},"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":"2026-09-25T13:52:27Z","match_totals_all":{"draws":2118,"losses":2225,"wins":1101},"match_totals_tracks":{"highest":{"draws":778,"losses":657,"wins":471},"medium":{"draws":767,"losses":863,"wins":338},"none":{"draws":573,"losses":705,"wins":292}},"model_slug":"meta-muse-glimmer-30b","overall":{"max":45.37253694835636,"mean":24.457685517154246,"min":6.328311136424571},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":60,"overall_ranking_status":"ranked","per_game":{"GB2-01":32.03694030645199,"GB2-02":15.966970879743966,"GB2-03":31.333463916130018,"GB2-04":27.427715764746406,"GB2-05":45.37253694835636,"GB2-07":42.90233392575276,"GB2-08":24.41122888408428},"per_game_all":{"GB2-01":29.890569876168644,"GB2-03":26.13250190743665,"GB2-04":21.22757812044362,"GB2-05":23.994217650243527,"GB2-07":36.18433568377046,"GB2-08":23.911910837816702},"per_game_match_totals_all":{"GB2-01":{"draws":217,"losses":362,"wins":157},"GB2-02":{"draws":462,"losses":26,"wins":2},"GB2-03":{"draws":298,"losses":256,"wins":172},"GB2-04":{"draws":558,"losses":186,"wins":102},"GB2-05":{"draws":0,"losses":567,"wins":199},"GB2-06":{"draws":2,"losses":199,"wins":55},"GB2-07":{"draws":0,"losses":462,"wins":374},"GB2-08":{"draws":581,"losses":167,"wins":40}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":75,"losses":112,"wins":41},"GB2-02":{"draws":232,"losses":13,"wins":1},"GB2-03":{"draws":111,"losses":76,"wins":47},"GB2-04":{"draws":169,"losses":72,"wins":61},"GB2-05":{"draws":0,"losses":177,"wins":137},"GB2-07":{"draws":0,"losses":151,"wins":167},"GB2-08":{"draws":191,"losses":56,"wins":17}},"medium":{"GB2-01":{"draws":71,"losses":136,"wins":31},"GB2-02":{"draws":230,"losses":13,"wins":1},"GB2-03":{"draws":82,"losses":105,"wins":61},"GB2-04":{"draws":185,"losses":41,"wins":20},"GB2-05":{"draws":0,"losses":177,"wins":43},"GB2-06":{"draws":2,"losses":199,"wins":55},"GB2-07":{"draws":0,"losses":136,"wins":116},"GB2-08":{"draws":197,"losses":56,"wins":11}},"none":{"GB2-01":{"draws":71,"losses":114,"wins":85},"GB2-03":{"draws":105,"losses":75,"wins":64},"GB2-04":{"draws":204,"losses":73,"wins":21},"GB2-05":{"draws":0,"losses":213,"wins":19},"GB2-07":{"draws":0,"losses":175,"wins":91},"GB2-08":{"draws":193,"losses":55,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1304.0050476725337,"GB2-03":1377.3211103370766,"GB2-04":1465.2974605862266,"GB2-05":1098.0739491044312,"GB2-07":1337.386146766564,"GB2-08":1314.4063047145662},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1334.8405122937986,"GB2-02":1466.5747369427895,"GB2-03":1433.0818669469777,"GB2-04":1505.4979397865784,"GB2-05":1434.8861380916906,"GB2-07":1436.0098804966221,"GB2-08":1320.9198277734108},"medium":{"GB2-01":1208.4108885699306,"GB2-02":1405.1719021757642,"GB2-03":1283.4809249094064,"GB2-04":1465.097484815574,"GB2-05":1040.810738244802,"GB2-06":1041.1249118223438,"GB2-07":1323.882208334911,"GB2-08":1313.1836103666499},"none":{"GB2-01":1368.763742153872,"GB2-03":1415.400539154845,"GB2-04":1425.2969571565277,"GB2-05":818.5249709768012,"GB2-07":1252.2663514681587,"GB2-08":1309.115476003638}},"per_game_tracks":{"highest":{"GB2-01":32.03694030645199,"GB2-02":15.966970879743966,"GB2-03":31.333463916130018,"GB2-04":27.427715764746406,"GB2-05":45.37253694835636,"GB2-07":42.90233392575276,"GB2-08":24.41122888408428},"medium":{"GB2-01":23.0126853545906,"GB2-02":7.305194459653427,"GB2-03":17.341929439664884,"GB2-04":20.956344911843157,"GB2-05":20.281804865949653,"GB2-06":22.879468141442242,"GB2-07":35.202863811457455,"GB2-08":23.82381936834102},"none":{"GB2-01":34.62208396746334,"GB2-03":29.72211236651506,"GB2-04":15.298673684741303,"GB2-05":6.328311136424571,"GB2-07":30.447809314101196,"GB2-08":23.50068426102481}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":30.320887892682467,"medium":21.350513794117806,"none":21.701654864662462},"reasoning_agg":{"highest":{"max":45.37253694835636,"mean":30.320887892682467,"min":15.966970879743966},"medium":{"max":35.202863811457455,"mean":21.350513794117806,"min":7.305194459653427},"none":{"max":34.62208396746334,"mean":21.701654864662462,"min":6.328311136424571}},"reasoning_labels":{"highest":"XHigh","medium":"Medium","none":"Low"},"reasoning_settings":{"balanced":"medium","baseline":"low","intensive":"xhigh"},"score_diagnostics":{"ceiling_score":45.37253694835636,"expected_score":23.052742251220916,"reasoning_variance":8.970374098564662,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.4049432659333299},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":45.37253694835636,"expected_score":21.889884429174895,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-8.431003463507572},"medium":{"ceiling_score":35.202863811457455,"expected_score":17.937847245177757,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.4126665489400487},"none":{"ceiling_score":34.62208396746334,"expected_score":22.492137964926403,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.7904831002639412}}},{"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":0.045998199999999996},"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":0.0625307},"codegen_latency_ms":{"attempt_count":23,"max_ms":550842,"mean_ms":222264.07142857142,"min_ms":41984,"run_count":14},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":15,"max_ms":550842,"mean_ms":354649.85714285716,"min_ms":219950,"run_count":7},"none":{"attempt_count":8,"max_ms":161392,"mean_ms":89878.28571428571,"min_ms":41984,"run_count":7}},"codegen_output_tokens":{"attempt_count":23,"output_max":12552,"output_mean":5500.928571428572,"output_min":1283,"run_count":14},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":15,"output_max":12552,"output_mean":8851.57142857143,"output_min":6019,"run_count":7},"none":{"attempt_count":8,"output_max":4235,"output_mean":2150.285714285714,"output_min":1283,"run_count":7}},"display_name":"Gemma 4 31B","economics":{"medium":30.604032464852885,"none":22.312855735333248},"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":"2026-09-25T15:10:59Z","match_totals_all":{"draws":569,"losses":1160,"wins":593},"match_totals_tracks":{"medium":{"draws":180,"losses":475,"wins":297},"none":{"draws":389,"losses":685,"wins":296}},"model_slug":"google-gemma-4-31b-it","overall":{"max":50.26394857772395,"mean":24.03887590211112,"min":12.918261292629804},"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":73,"wins":102},"GB2-04":{"draws":341,"losses":57,"wins":40},"GB2-05":{"draws":0,"losses":273,"wins":171},"GB2-06":{"draws":3,"losses":329,"wins":128},"GB2-07":{"draws":0,"losses":352,"wins":138},"GB2-08":{"draws":176,"losses":76,"wins":14}},"per_game_match_totals_tracks":{"medium":{"GB2-04":{"draws":180,"losses":23,"wins":15},"GB2-05":{"draws":0,"losses":109,"wins":127},"GB2-06":{"draws":0,"losses":177,"wins":61},"GB2-07":{"draws":0,"losses":166,"wins":94}},"none":{"GB2-01":{"draws":49,"losses":73,"wins":102},"GB2-04":{"draws":161,"losses":34,"wins":25},"GB2-05":{"draws":0,"losses":164,"wins":44},"GB2-06":{"draws":3,"losses":152,"wins":67},"GB2-07":{"draws":0,"losses":186,"wins":44},"GB2-08":{"draws":176,"losses":76,"wins":14}}},"per_game_raw_elo_tracks":{"medium":{"GB2-04":1460.2757496518636,"GB2-05":1516.0078875378504,"GB2-06":1049.0332225783065,"GB2-07":1228.862062366313},"none":{"GB2-01":1456.5486662112273,"GB2-04":1413.301181523511,"GB2-05":996.4721889908689,"GB2-06":1089.7617560473384,"GB2-07":1006.15809921059,"GB2-08":1305.335449504434}},"per_game_tracks":{"medium":{"GB2-04":19.990322662694933,"GB2-05":50.26394857772395,"GB2-06":23.30140252649068,"GB2-07":28.86045609250197},"none":{"GB2-01":40.745990007722504,"GB2-04":12.918261292629804,"GB2-05":17.441769674969127,"GB2-06":25.706276161565984,"GB2-07":13.829926370851808,"GB2-08":23.234910904260282}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.60842335630734,"none":21.469328447914894},"reasoning_agg":{"medium":{"max":50.26394857772395,"mean":26.60842335630734,"min":19.990322662694933},"none":{"max":40.745990007722504,"mean":21.469328447914894,"min":12.918261292629804}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":50.26394857772395,"reasoning_variance":5.1390949083924475},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":50.26394857772395,"expected_score":29.604862936261714,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.996439579954373},"none":{"ceiling_score":40.745990007722504,"expected_score":19.564270144509464,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.9050583034054291}}},{"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":0.3876148499999999},"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":0.07763975},"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":0.07206399999999999}},"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":0.07763974999999998},"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":0.38761484999999996}},"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":0.5373185999999999},"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":24.786783363952473,"highest":27.23956902599473,"medium":23.891737064640214,"none":23.22904400122249},"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":"2026-09-25T14:11:37Z","match_totals_all":{"draws":2412,"losses":3001,"wins":1336},"match_totals_tracks":{"highest":{"draws":794,"losses":1004,"wins":563},"medium":{"draws":777,"losses":1072,"wins":443},"none":{"draws":841,"losses":925,"wins":330}},"model_slug":"thinkingmachines-inkling-small","overall":{"max":57.00973194901733,"mean":23.838365602331503,"min":4.881426142579081},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":62,"overall_ranking_status":"ranked","per_game":{"GB2-01":28.35256079649359,"GB2-02":10.433188741667081,"GB2-03":28.343796015821606,"GB2-04":15.740585261422419,"GB2-05":40.13255458513899,"GB2-06":51.611716687770866,"GB2-07":20.225896354434745,"GB2-08":23.076253765208513},"per_game_all":{"GB2-01":18.847991410618558,"GB2-02":11.317484656603824,"GB2-03":30.661166541374797,"GB2-04":18.441488773777206,"GB2-05":21.662429672685807,"GB2-06":35.19562193016623,"GB2-07":37.36174876193255,"GB2-08":24.80633516446083},"per_game_match_totals_all":{"GB2-01":{"draws":164,"losses":480,"wins":105},"GB2-02":{"draws":720,"losses":88,"wins":2},"GB2-03":{"draws":307,"losses":245,"wins":223},"GB2-04":{"draws":562,"losses":215,"wins":134},"GB2-05":{"draws":0,"losses":583,"wins":160},"GB2-06":{"draws":9,"losses":571,"wins":296},"GB2-07":{"draws":0,"losses":542,"wins":373},"GB2-08":{"draws":650,"losses":277,"wins":43}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":81,"losses":110,"wins":51},"GB2-02":{"draws":258,"losses":48,"wins":0},"GB2-03":{"draws":76,"losses":110,"wins":100},"GB2-04":{"draws":171,"losses":86,"wins":38},"GB2-05":{"draws":0,"losses":156,"wins":125},"GB2-06":{"draws":5,"losses":166,"wins":179},"GB2-07":{"draws":0,"losses":213,"wins":59},"GB2-08":{"draws":203,"losses":115,"wins":11}},"medium":{"GB2-01":{"draws":37,"losses":208,"wins":7},"GB2-02":{"draws":232,"losses":12,"wins":0},"GB2-03":{"draws":91,"losses":91,"wins":63},"GB2-04":{"draws":186,"losses":77,"wins":59},"GB2-05":{"draws":0,"losses":205,"wins":25},"GB2-06":{"draws":2,"losses":202,"wins":55},"GB2-07":{"draws":0,"losses":163,"wins":214},"GB2-08":{"draws":229,"losses":114,"wins":20}},"none":{"GB2-01":{"draws":46,"losses":162,"wins":47},"GB2-02":{"draws":230,"losses":28,"wins":2},"GB2-03":{"draws":140,"losses":44,"wins":60},"GB2-04":{"draws":205,"losses":52,"wins":37},"GB2-05":{"draws":0,"losses":222,"wins":10},"GB2-06":{"draws":2,"losses":203,"wins":62},"GB2-07":{"draws":0,"losses":166,"wins":100},"GB2-08":{"draws":218,"losses":48,"wins":12}}},"per_game_raw_elo_all":{"GB2-01":1149.716959678628,"GB2-02":1432.4889723544231,"GB2-03":1424.7259260830153,"GB2-04":1445.9169968849328,"GB2-05":1061.2759014982773,"GB2-06":1243.6169848822126,"GB2-07":1354.0335086895432,"GB2-08":1323.8623776188224},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1282.677883060552,"GB2-02":1424.6576556254138,"GB2-03":1398.7927382313237,"GB2-04":1428.3415254636288,"GB2-05":1352.9565811557159,"GB2-06":1513.2308172983269,"GB2-07":1099.4800470371417,"GB2-08":1300.7855986250888},"medium":{"GB2-01":954.7891752047293,"GB2-02":1441.8149010053573,"GB2-03":1397.3932195649575,"GB2-04":1467.2184540066644,"GB2-05":1001.7884429744031,"GB2-06":1068.216179133427,"GB2-07":1644.67704856788,"GB2-08":1319.773428227486},"none":{"GB2-01":1211.6838207706028,"GB2-02":1430.9943604324985,"GB2-03":1477.9918204527644,"GB2-04":1442.1910111845057,"GB2-05":829.0826803647128,"GB2-06":1149.403958214884,"GB2-07":1317.9434304636081,"GB2-08":1351.0281060038924}},"per_game_tracks":{"highest":{"GB2-01":28.35256079649359,"GB2-02":10.433188741667081,"GB2-03":28.343796015821606,"GB2-04":15.740585261422419,"GB2-05":40.13255458513899,"GB2-06":51.611716687770866,"GB2-07":20.225896354434745,"GB2-08":23.076253765208513},"medium":{"GB2-01":4.881426142579081,"GB2-02":12.465517805734288,"GB2-03":28.03443283640638,"GB2-04":21.758731660036542,"GB2-05":17.86158687607802,"GB2-06":24.524475172908698,"GB2-07":57.00973194901733,"GB2-08":24.597994074361377},"none":{"GB2-01":23.309987292783003,"GB2-02":11.053747422410106,"GB2-03":35.60527077189641,"GB2-04":17.825149399872654,"GB2-05":6.993147556840411,"GB2-06":29.450673929819136,"GB2-07":34.8496179823456,"GB2-08":26.744757653812606}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":25.761593839197328,"medium":23.19848351335541,"none":22.555019454441762},"reasoning_agg":{"highest":{"max":51.611716687770866,"mean":25.761593839197328,"min":10.433188741667081},"medium":{"max":57.00973194901733,"mean":23.19848351335541,"min":4.881426142579081},"none":{"max":35.60527077189641,"mean":22.555019454441762,"min":6.993147556840411}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":57.00973194901733,"expected_score":20.106928325377876,"reasoning_variance":3.206574384755566,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-3.7314372769536277},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":51.611716687770866,"expected_score":16.443027601120587,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.318566238076741},"medium":{"ceiling_score":57.00973194901733,"expected_score":21.18057892673537,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-2.0179045866200376},"none":{"ceiling_score":35.60527077189641,"expected_score":22.697178448277665,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.1421589938359027}}},{"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":0.5047206500000001},"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":0.31772779999999995},"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":0.38919240000000005}},"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":1.21164085},"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":33.471528788456645,"highest":24.21543621287482,"medium":26.716578014107217,"none":28.154386641135257},"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":"2026-09-25T12:33:28Z","match_totals_all":{"draws":1724,"losses":1760,"wins":853},"match_totals_tracks":{"highest":{"draws":870,"losses":689,"wins":308},"medium":{"draws":416,"losses":457,"wins":255},"none":{"draws":438,"losses":614,"wins":290}},"model_slug":"nvidia-nemotron-3-ultra-550b-a55b","overall":{"max":54.629833111248594,"mean":23.492194258414813,"min":4.923730589416949},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":63,"overall_ranking_status":"partial","per_game":{"GB2-01":25.687756439022323,"GB2-02":8.523437707990063,"GB2-04":13.307756675211982,"GB2-05":36.88732222284614,"GB2-06":37.7955878292642,"GB2-08":23.090756402914224},"per_game_all":{"GB2-01":37.68836169631389,"GB2-06":38.64174993975658,"GB2-08":24.084474729299476},"per_game_match_totals_all":{"GB2-01":{"draws":128,"losses":259,"wins":183},"GB2-02":{"draws":520,"losses":77,"wins":7},"GB2-03":{"draws":77,"losses":49,"wins":12},"GB2-04":{"draws":314,"losses":68,"wins":30},"GB2-05":{"draws":0,"losses":290,"wins":262},"GB2-06":{"draws":32,"losses":349,"wins":258},"GB2-07":{"draws":0,"losses":402,"wins":52},"GB2-08":{"draws":653,"losses":266,"wins":49}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":56,"losses":118,"wins":38},"GB2-02":{"draws":336,"losses":46,"wins":6},"GB2-04":{"draws":156,"losses":44,"wins":12},"GB2-05":{"draws":0,"losses":217,"wins":155},"GB2-06":{"draws":16,"losses":116,"wins":75},"GB2-08":{"draws":306,"losses":148,"wins":22}},"medium":{"GB2-01":{"draws":39,"losses":72,"wins":77},"GB2-02":{"draws":184,"losses":31,"wins":1},"GB2-06":{"draws":14,"losses":84,"wins":128},"GB2-07":{"draws":0,"losses":210,"wins":32},"GB2-08":{"draws":179,"losses":60,"wins":17}},"none":{"GB2-01":{"draws":33,"losses":69,"wins":68},"GB2-03":{"draws":77,"losses":49,"wins":12},"GB2-04":{"draws":158,"losses":24,"wins":18},"GB2-05":{"draws":0,"losses":73,"wins":107},"GB2-06":{"draws":2,"losses":149,"wins":55},"GB2-07":{"draws":0,"losses":192,"wins":20},"GB2-08":{"draws":168,"losses":58,"wins":10}}},"per_game_raw_elo_all":{"GB2-01":1416.2647345059047,"GB2-06":1304.5044983084274,"GB2-08":1317.6509304947183},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1247.2566040724391,"GB2-02":1416.916593140943,"GB2-04":1416.3822018342894,"GB2-05":1306.8643133669477,"GB2-06":1290.8680313592329,"GB2-08":1304.842053061372},"medium":{"GB2-01":1450.6138129385795,"GB2-02":1407.9560390913514,"GB2-06":1568.3989131462947,"GB2-07":893.9437869150827,"GB2-08":1328.808197108261},"none":{"GB2-01":1550.923786506695,"GB2-03":1328.8177773893021,"GB2-04":1491.7851386586212,"GB2-05":1545.422857529501,"GB2-06":1054.246550419755,"GB2-07":874.362902625652,"GB2-08":1319.3025413145217}},"per_game_tracks":{"highest":{"GB2-01":25.687756439022323,"GB2-02":8.523437707990063,"GB2-04":13.307756675211982,"GB2-05":36.88732222284614,"GB2-06":37.7955878292642,"GB2-08":23.090756402914224},"medium":{"GB2-01":40.14634293665803,"GB2-02":7.4721350280143835,"GB2-06":54.629833111248594,"GB2-07":6.3532038338859245,"GB2-08":24.98137516072915},"none":{"GB2-01":47.23098571326132,"GB2-03":20.796958527790924,"GB2-04":24.567731347266125,"GB2-05":51.8801788071995,"GB2-06":23.49982887875695,"GB2-07":4.923730589416949,"GB2-08":24.181292624255057}},"provider_color":"#76B900","provider_company":"NVIDIA","provider_key":"nvidia","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":20.971182924071233,"medium":23.065491033644633,"none":26.43990881752858},"reasoning_agg":{"highest":{"max":37.7955878292642,"mean":20.971182924071233,"min":8.523437707990063},"medium":{"max":54.629833111248594,"mean":23.065491033644633,"min":6.3532038338859245},"none":{"max":51.8801788071995,"mean":26.43990881752858,"min":4.923730589416949}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":54.629833111248594,"expected_score":27.60303128051258,"reasoning_variance":5.468725893457346,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.110837022097769},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":37.7955878292642,"expected_score":13.172244657473987,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.798938266597245},"medium":{"ceiling_score":54.629833111248594,"expected_score":24.640967391476472,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.575476357831839},"none":{"ceiling_score":51.8801788071995,"expected_score":27.884437863675117,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":1.4445290461465383}}},{"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":18.8178035929424,"none":30.376605494931567},"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":"2026-09-25T15:19:38Z","match_totals_all":{"draws":879,"losses":1392,"wins":745},"match_totals_tracks":{"medium":{"draws":573,"losses":791,"wins":296},"none":{"draws":306,"losses":601,"wins":449}},"model_slug":"minimax-minimax-m3","overall":{"max":42.47095379427678,"mean":23.2342990481235,"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":212,"wins":152},"GB2-02":{"draws":374,"losses":73,"wins":1},"GB2-03":{"draws":57,"losses":64,"wins":55},"GB2-04":{"draws":172,"losses":34,"wins":20},"GB2-05":{"draws":0,"losses":386,"wins":94},"GB2-06":{"draws":1,"losses":164,"wins":75},"GB2-07":{"draws":0,"losses":284,"wins":212},"GB2-08":{"draws":221,"losses":175,"wins":136}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":11,"losses":132,"wins":51},"GB2-02":{"draws":185,"losses":31,"wins":0},"GB2-04":{"draws":172,"losses":34,"wins":20},"GB2-05":{"draws":0,"losses":248,"wins":4},"GB2-06":{"draws":1,"losses":164,"wins":75},"GB2-07":{"draws":0,"losses":120,"wins":130},"GB2-08":{"draws":204,"losses":62,"wins":16}},"none":{"GB2-01":{"draws":43,"losses":80,"wins":101},"GB2-02":{"draws":189,"losses":42,"wins":1},"GB2-03":{"draws":57,"losses":64,"wins":55},"GB2-05":{"draws":0,"losses":138,"wins":90},"GB2-07":{"draws":0,"losses":164,"wins":82},"GB2-08":{"draws":17,"losses":113,"wins":120}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1170.1433865299655,"GB2-02":1419.2500566846154,"GB2-04":1391.7572226694713,"GB2-05":716.9732845937543,"GB2-06":1105.2901358809513,"GB2-07":1420.5301665145182,"GB2-08":1321.1854784744369},"none":{"GB2-01":1426.9041066181655,"GB2-02":1410.9106514889643,"GB2-03":1442.5735751880513,"GB2-05":1256.4377579120328,"GB2-07":1207.8219281213146,"GB2-08":1559.443424206279}},"per_game_tracks":{"medium":{"GB2-01":20.07046347802326,"GB2-02":9.062637566537523,"GB2-04":9.720348794092118,"GB2-05":0.0,"GB2-06":26.7057657786473,"GB2-07":41.673700863833744,"GB2-08":24.49170866946286},"none":{"GB2-01":38.62063436503806,"GB2-02":8.021854667018928,"GB2-03":31.852211767076273,"GB2-05":33.89005402357793,"GB2-07":27.40392435260142,"GB2-08":42.47095379427678}},"provider_color":"#00BFA5","provider_company":"MiniMax","provider_key":"minimax","provider_text_color":"#f2fffc","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":18.199981419636146,"none":28.26861667661085},"reasoning_agg":{"medium":{"max":41.673700863833744,"mean":18.199981419636146,"min":0.0},"none":{"max":42.47095379427678,"mean":28.26861667661085,"min":8.021854667018928}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":42.47095379427678,"reasoning_variance":10.068635256974705},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":41.673700863833744,"expected_score":16.27126690985613,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.928714509780015},"none":{"ceiling_score":42.47095379427678,"expected_score":32.54839992867792,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.279783252067066}}},{"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":0.486187507},"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":0.21411433159999999},"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":0.038219742999999994},"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":0.030685472799999995},"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":0.7524538072000001},"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":23.201251982956503,"highest":25.491686551767373,"medium":24.816161020658885,"none":25.848879605846548},"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":"2026-09-25T15:19:38Z","match_totals_all":{"draws":2867,"losses":3273,"wins":1700},"match_totals_tracks":{"highest":{"draws":593,"losses":310,"wins":121},"medium":{"draws":1313,"losses":1338,"wins":701},"none":{"draws":961,"losses":1625,"wins":878}},"model_slug":"xiaomi-mimo-v2-5","overall":{"max":48.979799568566214,"mean":22.87569332665649,"min":6.460914561290655},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["missing_or_non_distinct_settings","untested_or_ineligible_settings"],"overall_official_rank":65,"overall_ranking_status":"partial","per_game":{"GB2-01":23.46942855390865,"GB2-02":13.398467888140017,"GB2-04":15.91085216964937,"GB2-06":48.979799568566214,"GB2-08":25.699884578572615},"per_game_all":{"GB2-01":29.229640489682442,"GB2-02":10.462593350052165,"GB2-04":15.41196553885785,"GB2-06":37.940310768939064,"GB2-08":22.961749767250996},"per_game_match_totals_all":{"GB2-01":{"draws":243,"losses":558,"wins":327},"GB2-02":{"draws":894,"losses":136,"wins":32},"GB2-03":{"draws":70,"losses":43,"wins":37},"GB2-04":{"draws":895,"losses":258,"wins":105},"GB2-05":{"draws":0,"losses":615,"wins":383},"GB2-06":{"draws":29,"losses":639,"wins":428},"GB2-07":{"draws":0,"losses":616,"wins":326},"GB2-08":{"draws":736,"losses":408,"wins":62}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":85,"losses":71,"wins":2},"GB2-02":{"draws":157,"losses":34,"wins":9},"GB2-04":{"draws":159,"losses":37,"wins":16},"GB2-06":{"draws":12,"losses":119,"wins":91},"GB2-08":{"draws":180,"losses":49,"wins":3}},"medium":{"GB2-01":{"draws":49,"losses":214,"wins":133},"GB2-02":{"draws":563,"losses":75,"wins":22},"GB2-04":{"draws":439,"losses":146,"wins":49},"GB2-05":{"draws":0,"losses":261,"wins":185},"GB2-06":{"draws":11,"losses":165,"wins":68},"GB2-07":{"draws":0,"losses":286,"wins":188},"GB2-08":{"draws":251,"losses":191,"wins":56}},"none":{"GB2-01":{"draws":109,"losses":273,"wins":192},"GB2-02":{"draws":174,"losses":27,"wins":1},"GB2-03":{"draws":70,"losses":43,"wins":37},"GB2-04":{"draws":297,"losses":75,"wins":40},"GB2-05":{"draws":0,"losses":354,"wins":198},"GB2-06":{"draws":6,"losses":355,"wins":269},"GB2-07":{"draws":0,"losses":330,"wins":138},"GB2-08":{"draws":305,"losses":168,"wins":3}}},"per_game_raw_elo_all":{"GB2-01":1303.452604687618,"GB2-02":1435.1157385808792,"GB2-04":1435.6924140205144,"GB2-06":1296.934429210419,"GB2-08":1308.0394511612478},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1234.61584720606,"GB2-02":1467.166005128762,"GB2-04":1449.0490320389179,"GB2-06":1489.5775244954111,"GB2-08":1354.476054487212},"medium":{"GB2-01":1309.2195945488988,"GB2-02":1436.485031531869,"GB2-04":1415.837514261648,"GB2-05":1282.8542233064363,"GB2-06":1148.1864008170126,"GB2-07":1246.7684906280847,"GB2-08":1317.8174654587317},"none":{"GB2-01":1366.5223723078952,"GB2-02":1401.6961790820071,"GB2-03":1486.0560424806201,"GB2-04":1442.1906957609772,"GB2-05":1275.6122520189124,"GB2-06":1253.0393623188336,"GB2-07":1155.2246707720728,"GB2-08":1251.8248335378}},"per_game_tracks":{"highest":{"GB2-01":23.46942855390865,"GB2-02":13.398467888140017,"GB2-04":15.91085216964937,"GB2-06":48.979799568566214,"GB2-08":25.699884578572615},"medium":{"GB2-01":30.060296329002895,"GB2-02":11.528397600725828,"GB2-04":13.182482558250914,"GB2-05":35.53404787217864,"GB2-06":29.3094167434742,"GB2-07":29.97891004726828,"GB2-08":24.11957599371145},"none":{"GB2-01":34.15919658613578,"GB2-02":6.460914561290655,"GB2-03":35.70563172240146,"GB2-04":17.142561888673264,"GB2-05":34.88953366402243,"GB2-06":35.53171599477679,"GB2-07":23.83569370000309,"GB2-08":19.06578872946892}},"provider_color":"#FF6900","provider_company":"Xiaomi","provider_key":"xiaomi","provider_text_color":"#fff7f1","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":22.665670661087013,"medium":22.4239328201719,"none":23.537476498710557},"reasoning_agg":{"highest":{"max":48.979799568566214,"mean":22.665670661087013,"min":13.398467888140017},"medium":{"max":35.53404787217864,"mean":22.4239328201719,"min":11.528397600725828},"none":{"max":35.70563172240146,"mean":23.537476498710557,"min":6.460914561290655}},"reasoning_labels":{"highest":"High","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":48.979799568566214,"expected_score":18.829080767225115,"reasoning_variance":1.113543678538658,"reliability_score":96.0560927788669,"uncertainty_avg":3.943907221133107,"uncertainty_penalty":-4.046612559431374},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":48.979799568566214,"expected_score":16.989632405084286,"reliability_score":88.16827833660068,"uncertainty_avg":11.831721663399323,"uncertainty_penalty":-5.676038256002727},"medium":{"ceiling_score":35.53404787217864,"expected_score":23.371111872528445,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.947179052356546},"none":{"ceiling_score":35.70563172240146,"expected_score":26.002277191411686,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.464800692701129}}},{"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":0.5884539499999999},"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":4.15725071}},"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":26.84431437876965,"highest":27.48988573112342,"medium":23.298318032066064,"none":28.224103029781716},"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":"2026-09-25T13:16:57Z","match_totals_all":{"draws":2641,"losses":3905,"wins":1816},"match_totals_tracks":{"highest":{"draws":1167,"losses":1726,"wins":753},"medium":{"draws":706,"losses":1039,"wins":409},"none":{"draws":768,"losses":1140,"wins":654}},"model_slug":"thinkingmachines-inkling","overall":{"max":59.97193472120926,"mean":22.76811532013747,"min":7.957773475504234},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["below_generation_quality_threshold"],"overall_official_rank":66,"overall_ranking_status":"partial","per_game":{"GB2-01":25.196890039181877,"GB2-02":8.759478344679279,"GB2-03":31.713474611999153,"GB2-04":20.86000846438864,"GB2-05":23.922871015070534,"GB2-06":53.98273918474334,"GB2-07":35.73196065042729,"GB2-08":19.75166353849725},"per_game_all":{"GB2-01":26.25453257609752,"GB2-03":36.04927126853777,"GB2-04":13.042709396366211,"GB2-05":26.078058918300844,"GB2-07":24.76414503161301,"GB2-08":34.87716908170255},"per_game_match_totals_all":{"GB2-01":{"draws":402,"losses":622,"wins":116},"GB2-02":{"draws":537,"losses":63,"wins":8},"GB2-03":{"draws":324,"losses":361,"wins":382},"GB2-04":{"draws":824,"losses":251,"wins":131},"GB2-05":{"draws":0,"losses":1029,"wins":363},"GB2-06":{"draws":20,"losses":402,"wins":336},"GB2-07":{"draws":0,"losses":774,"wins":268},"GB2-08":{"draws":534,"losses":403,"wins":212}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":137,"losses":205,"wins":16},"GB2-02":{"draws":337,"losses":41,"wins":4},"GB2-03":{"draws":157,"losses":151,"wins":122},"GB2-04":{"draws":264,"losses":88,"wins":66},"GB2-05":{"draws":0,"losses":599,"wins":155},"GB2-06":{"draws":15,"losses":226,"wins":253},"GB2-07":{"draws":0,"losses":265,"wins":133},"GB2-08":{"draws":257,"losses":151,"wins":4}},"medium":{"GB2-01":{"draws":117,"losses":182,"wins":67},"GB2-03":{"draws":62,"losses":111,"wins":164},"GB2-04":{"draws":261,"losses":57,"wins":14},"GB2-05":{"draws":0,"losses":171,"wins":71},"GB2-07":{"draws":0,"losses":341,"wins":57},"GB2-08":{"draws":266,"losses":177,"wins":36}},"none":{"GB2-01":{"draws":148,"losses":235,"wins":33},"GB2-02":{"draws":200,"losses":22,"wins":4},"GB2-03":{"draws":105,"losses":99,"wins":96},"GB2-04":{"draws":299,"losses":106,"wins":51},"GB2-05":{"draws":0,"losses":259,"wins":137},"GB2-06":{"draws":5,"losses":176,"wins":83},"GB2-07":{"draws":0,"losses":168,"wins":78},"GB2-08":{"draws":11,"losses":75,"wins":172}}},"per_game_raw_elo_all":{"GB2-01":1250.982273752252,"GB2-03":1481.6886936712745,"GB2-04":1409.8500269420365,"GB2-05":1130.821704191912,"GB2-07":1164.81760271004,"GB2-08":1455.116703613852},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1234.1136208078292,"GB2-02":1410.3826257930446,"GB2-03":1430.299023042923,"GB2-04":1458.5491498281401,"GB2-05":1092.2996731742678,"GB2-06":1549.1150032151852,"GB2-07":1326.6538472650284,"GB2-08":1254.6639903797159},"medium":{"GB2-01":1296.3053028064285,"GB2-03":1537.8806387963914,"GB2-04":1375.4511988255103,"GB2-05":1086.0713160839841,"GB2-07":979.2771944650718,"GB2-08":1321.1467474377516},"none":{"GB2-01":1222.5278976424986,"GB2-02":1420.974428697136,"GB2-03":1476.886419174509,"GB2-04":1395.5497321724583,"GB2-05":1214.094123317484,"GB2-06":1161.472768750128,"GB2-07":1188.52176640002,"GB2-08":1789.5393730240885}},"per_game_tracks":{"highest":{"GB2-01":25.196890039181877,"GB2-02":8.759478344679279,"GB2-03":31.713474611999153,"GB2-04":20.86000846438864,"GB2-05":23.922871015070534,"GB2-06":53.98273918474334,"GB2-07":35.73196065042729,"GB2-08":19.75166353849725},"medium":{"GB2-01":29.67228693230946,"GB2-03":41.59139577501191,"GB2-04":7.957773475504234,"GB2-05":23.21045764633968,"GB2-07":12.450085377829959,"GB2-08":24.907908985401132},"none":{"GB2-01":23.894420756801225,"GB2-02":9.390653049669545,"GB2-03":34.84294341860225,"GB2-04":10.310346249205763,"GB2-05":31.100848093492324,"GB2-06":30.171288882691577,"GB2-07":26.11038906658177,"GB2-08":59.97193472120926}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":23.806939390284235,"medium":18.231919146815006,"none":26.265487423313157},"reasoning_agg":{"highest":{"max":53.98273918474334,"mean":23.806939390284235,"min":8.759478344679279},"medium":{"max":41.59139577501191,"mean":18.231919146815006,"min":7.957773475504234},"none":{"max":59.97193472120926,"mean":26.265487423313157,"min":9.390653049669545}},"reasoning_labels":{"highest":"Max","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"max"},"score_diagnostics":{"ceiling_score":59.97193472120926,"expected_score":23.490716029720783,"reasoning_variance":8.033568276498151,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.7226007095833147},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":53.98273918474334,"expected_score":16.173213995869656,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-7.633725394414579},"medium":{"ceiling_score":41.59139577501191,"expected_score":23.68156256640798,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":5.449643419592974},"none":{"ceiling_score":59.97193472120926,"expected_score":29.0373096066757,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":2.7718221833625414}}},{"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":1.3975426639832813},"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":0.5409853360167187}},"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":0.5409853360167187},"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":1.9385279999999996},"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":26.017320074855167,"none":18.520382849552355},"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":"2026-09-25T14:21:56Z","match_totals_all":{"draws":1330,"losses":1678,"wins":571},"match_totals_tracks":{"highest":{"draws":719,"losses":816,"wins":367},"none":{"draws":611,"losses":862,"wins":204}},"model_slug":"mistralai-mistral-medium-3-5","overall":{"max":56.99034820792066,"mean":21.537725210435838,"min":3.83400018350949},"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":13.661100526328765,"GB2-03":28.792321610997423,"GB2-04":13.027941933509863,"GB2-05":56.99034820792066,"GB2-06":31.009077920581134,"GB2-07":16.002668622208688,"GB2-08":22.63778170243964},"per_game_match_totals_all":{"GB2-01":{"draws":27,"losses":194,"wins":11},"GB2-02":{"draws":445,"losses":94,"wins":11},"GB2-03":{"draws":152,"losses":191,"wins":127},"GB2-04":{"draws":301,"losses":137,"wins":45},"GB2-05":{"draws":0,"losses":301,"wins":185},"GB2-06":{"draws":15,"losses":344,"wins":119},"GB2-07":{"draws":0,"losses":248,"wins":42},"GB2-08":{"draws":390,"losses":169,"wins":31}},"per_game_match_totals_tracks":{"highest":{"GB2-02":{"draws":245,"losses":46,"wins":11},"GB2-03":{"draws":79,"losses":91,"wins":58},"GB2-04":{"draws":184,"losses":48,"wins":20},"GB2-05":{"draws":0,"losses":110,"wins":150},"GB2-06":{"draws":13,"losses":157,"wins":70},"GB2-07":{"draws":0,"losses":248,"wins":42},"GB2-08":{"draws":198,"losses":116,"wins":16}},"none":{"GB2-01":{"draws":27,"losses":194,"wins":11},"GB2-02":{"draws":200,"losses":48,"wins":0},"GB2-03":{"draws":73,"losses":100,"wins":69},"GB2-04":{"draws":117,"losses":89,"wins":25},"GB2-05":{"draws":0,"losses":191,"wins":35},"GB2-06":{"draws":2,"losses":187,"wins":49},"GB2-08":{"draws":192,"losses":53,"wins":15}}},"per_game_raw_elo_tracks":{"highest":{"GB2-02":1447.7289649498068,"GB2-03":1406.3861199840924,"GB2-04":1412.2686820058884,"GB2-05":1621.6007828704835,"GB2-06":1176.5381220136703,"GB2-07":1035.7067945105448,"GB2-08":1294.977609210738},"none":{"GB2-01":962.5786552315466,"GB2-02":1380.3171666207907,"GB2-03":1443.5594912825875,"GB2-04":1402.8619413155873,"GB2-05":1119.0368805636974,"GB2-06":1081.280252900736,"GB2-08":1344.2196973298408}},"per_game_tracks":{"highest":{"GB2-02":13.661100526328765,"GB2-03":28.792321610997423,"GB2-04":13.027941933509863,"GB2-05":56.99034820792066,"GB2-06":31.009077920581134,"GB2-07":16.002668622208688,"GB2-08":22.63778170243964},"none":{"GB2-01":5.364102567773256,"GB2-02":3.83400018350949,"GB2-03":32.358999465512234,"GB2-04":11.439966470700094,"GB2-05":25.23037696584976,"GB2-06":25.249093186396834,"GB2-08":26.16614110712482}},"provider_color":"#FF7000","provider_company":"Mistral","provider_key":"mistral","provider_text_color":"#fff8f3","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":25.16312488927676,"none":17.91232553159492},"reasoning_agg":{"highest":{"max":56.99034820792066,"mean":25.16312488927676,"min":13.027941933509863},"none":{"max":32.358999465512234,"mean":17.91232553159492,"min":3.83400018350949}},"reasoning_labels":{"highest":"High","medium":"Setting not tested","none":"None"},"reasoning_settings":{"baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":56.99034820792066,"reasoning_variance":7.250799357681839},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":56.99034820792066,"expected_score":14.647195671469023,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.515929217807736},"none":{"ceiling_score":32.358999465512234,"expected_score":16.465847993311407,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.4464775382835136}}},{"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":28.324277808502853,"none":21.057347774738698},"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":755,"losses":1340,"wins":499},"match_totals_tracks":{"medium":{"draws":405,"losses":666,"wins":331},"none":{"draws":350,"losses":674,"wins":168}},"model_slug":"cohere-north-mini-code","overall":{"max":48.748765419591805,"mean":21.051375112251986,"min":15.744039665353446},"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":148,"losses":253,"wins":43},"GB2-03":{"draws":45,"losses":94,"wins":13},"GB2-04":{"draws":173,"losses":44,"wins":15},"GB2-05":{"draws":0,"losses":106,"wins":130},"GB2-06":{"draws":3,"losses":171,"wins":60},"GB2-07":{"draws":0,"losses":535,"wins":229},"GB2-08":{"draws":386,"losses":137,"wins":9}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":45,"losses":94,"wins":13},"GB2-04":{"draws":173,"losses":44,"wins":15},"GB2-05":{"draws":0,"losses":106,"wins":130},"GB2-06":{"draws":3,"losses":171,"wins":60},"GB2-07":{"draws":0,"losses":185,"wins":113},"GB2-08":{"draws":184,"losses":66,"wins":0}},"none":{"GB2-01":{"draws":148,"losses":253,"wins":43},"GB2-07":{"draws":0,"losses":350,"wins":116},"GB2-08":{"draws":202,"losses":71,"wins":9}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1306.1751192514726,"GB2-04":1452.1308032078118,"GB2-05":1505.6920140889088,"GB2-06":1200.7278853564226,"GB2-07":1325.7235521183766,"GB2-08":1316.9228461053442},"none":{"GB2-01":1148.8249315169192,"GB2-07":1116.574474382739,"GB2-08":1305.0370526777124}},"per_game_tracks":{"medium":{"GB2-03":16.125411079300658,"GB2-04":16.308603127079742,"GB2-05":48.748765419591805,"GB2-06":31.499648290466038,"GB2-07":34.45222425187841,"GB2-08":22.811014682700467},"none":{"GB2-01":18.67245084542328,"GB2-07":21.234030707551817,"GB2-08":23.265561771241}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":26.358710559150524,"none":15.744039665353446},"reasoning_agg":{"medium":{"max":48.748765419591805,"mean":26.358710559150524,"min":16.125411079300658},"none":{"max":23.265561771241,"mean":15.744039665353446,"min":18.67245084542328}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":48.748765419591805,"reasoning_variance":10.614670893797078},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":48.748765419591805,"expected_score":28.812741005705636,"reliability_score":85.14861785164499,"uncertainty_avg":14.851382148355015,"uncertainty_penalty":2.4540304465551124},"none":{"ceiling_score":23.265561771241,"expected_score":18.939339279021805,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.195299613668359}}},{"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":0.010578220000000003},"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":0.007612509999999999}},"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":0.010122240000000001},"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":0.028312969999999996},"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":19.105895091452314,"highest":19.41544742908869,"medium":19.06070636578836,"none":26.056088009018758},"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":"2026-09-25T14:27:19Z","match_totals_all":{"draws":1867,"losses":2007,"wins":620},"match_totals_tracks":{"highest":{"draws":716,"losses":750,"wins":158},"medium":{"draws":602,"losses":741,"wins":166},"none":{"draws":549,"losses":516,"wins":296}},"model_slug":"inception-mercury-2-5-preview","overall":{"max":38.37213841472128,"mean":19.65786602912411,"min":10.772886758516659},"overall_eligibility_flag":true,"overall_ineligibility_reason_codes":[],"overall_official_rank":69,"overall_ranking_status":"ranked","per_game":{"GB2-01":29.334163810673346,"GB2-02":14.879637514716912,"GB2-04":14.494975929834537,"GB2-06":23.163090376598188,"GB2-07":15.029011268175418,"GB2-08":19.591805674533738},"per_game_all":{"GB2-02":13.894802576674953,"GB2-04":18.624552081674825,"GB2-06":24.798330616007163},"per_game_match_totals_all":{"GB2-01":{"draws":81,"losses":147,"wins":50},"GB2-02":{"draws":697,"losses":78,"wins":1},"GB2-03":{"draws":101,"losses":137,"wins":89},"GB2-04":{"draws":588,"losses":126,"wins":49},"GB2-05":{"draws":0,"losses":343,"wins":177},"GB2-06":{"draws":6,"losses":554,"wins":160},"GB2-07":{"draws":0,"losses":483,"wins":75},"GB2-08":{"draws":394,"losses":139,"wins":19}},"per_game_match_totals_tracks":{"highest":{"GB2-01":{"draws":81,"losses":147,"wins":50},"GB2-02":{"draws":245,"losses":24,"wins":1},"GB2-04":{"draws":205,"losses":49,"wins":14},"GB2-06":{"draws":3,"losses":195,"wins":44},"GB2-07":{"draws":0,"losses":248,"wins":42},"GB2-08":{"draws":182,"losses":87,"wins":7}},"medium":{"GB2-02":{"draws":217,"losses":11,"wins":0},"GB2-04":{"draws":171,"losses":44,"wins":16},"GB2-05":{"draws":0,"losses":211,"wins":51},"GB2-06":{"draws":2,"losses":188,"wins":54},"GB2-07":{"draws":0,"losses":235,"wins":33},"GB2-08":{"draws":212,"losses":52,"wins":12}},"none":{"GB2-02":{"draws":235,"losses":43,"wins":0},"GB2-03":{"draws":101,"losses":137,"wins":89},"GB2-04":{"draws":212,"losses":33,"wins":19},"GB2-05":{"draws":0,"losses":132,"wins":126},"GB2-06":{"draws":1,"losses":171,"wins":62}}},"per_game_raw_elo_all":{"GB2-02":1451.3018586466953,"GB2-04":1449.2719464399688,"GB2-06":1073.7127316633366},"per_game_raw_elo_tracks":{"highest":{"GB2-01":1294.656689306476,"GB2-02":1457.7005581154203,"GB2-04":1421.2283406234515,"GB2-06":1046.529413953533,"GB2-07":1021.1793636804248,"GB2-08":1256.9096105084075},"medium":{"GB2-02":1439.2021984898463,"GB2-04":1447.390731050095,"GB2-05":1077.15087262024,"GB2-06":1081.047870568292,"GB2-07":958.6159767874869,"GB2-08":1334.5935405101955},"none":{"GB2-02":1457.00281933482,"GB2-03":1392.361021000484,"GB2-04":1479.1967676463596,"GB2-05":1326.0360262339282,"GB2-06":1093.5609104681846}},"per_game_tracks":{"highest":{"GB2-01":29.334163810673346,"GB2-02":14.879637514716912,"GB2-04":14.494975929834537,"GB2-06":23.163090376598188,"GB2-07":15.029011268175418,"GB2-08":19.591805674533738},"medium":{"GB2-02":11.973977531323163,"GB2-04":18.16135373748405,"GB2-05":22.711376551122164,"GB2-06":25.25431191745537,"GB2-07":10.772886758516659,"GB2-08":25.490331698828758},"none":{"GB2-02":14.830792683984784,"GB2-03":27.88259281471392,"GB2-04":23.217326577705883,"GB2-05":38.37213841472128,"GB2-06":25.977589553967935}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":18.068109719151302,"medium":17.73798596192097,"none":23.167502406300063},"reasoning_agg":{"highest":{"max":29.334163810673346,"mean":18.068109719151302,"min":14.494975929834537},"medium":{"max":25.490331698828758,"mean":17.73798596192097,"min":10.772886758516659},"none":{"max":38.37213841472128,"mean":23.167502406300063,"min":14.830792683984784}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"None"},"reasoning_settings":{"balanced":"medium","baseline":"none","intensive":"high"},"score_diagnostics":{"ceiling_score":38.37213841472128,"expected_score":13.3604245527985,"reasoning_variance":5.429516444379093,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-6.297441476325611},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":29.334163810673346,"expected_score":8.191141442900676,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.876968276250626},"medium":{"ceiling_score":25.490331698828758,"expected_score":17.115009574374742,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.6229763875462275},"none":{"ceiling_score":38.37213841472128,"expected_score":26.88491929702358,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.7174168907235163}}},{"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":0.8197712500000001},"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":3.40579925},"codegen_latency_ms":{"attempt_count":53,"max_ms":1200477,"mean_ms":895711.875,"min_ms":390884,"run_count":24},"codegen_latency_ms_by_reasoning":{"medium":{"attempt_count":17,"max_ms":1097898,"mean_ms":822157.625,"min_ms":490730,"run_count":8},"none":{"attempt_count":36,"max_ms":1200477,"mean_ms":932489.0,"min_ms":390884,"run_count":16}},"codegen_output_tokens":{"attempt_count":53,"output_max":142709,"output_mean":109998.5,"output_min":55627,"run_count":24},"codegen_output_tokens_by_reasoning":{"medium":{"attempt_count":17,"output_max":131072,"output_mean":95066.75,"output_min":57337,"run_count":8},"none":{"attempt_count":36,"output_max":142709,"output_mean":117464.375,"output_min":55627,"run_count":16}},"display_name":"Nex N2 Pro","economics":{"medium":19.193013347430895,"none":25.922021453852462},"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":"2026-09-25T16:02:53Z","match_totals_all":{"draws":781,"losses":1324,"wins":553},"match_totals_tracks":{"medium":{"draws":120,"losses":774,"wins":222},"none":{"draws":661,"losses":550,"wins":331}},"model_slug":"nex-agi-nex-n2-pro","overall":{"max":64.55194498926986,"mean":19.07367324525054,"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":175,"losses":41,"wins":6},"GB2-03":{"draws":157,"losses":99,"wins":42},"GB2-04":{"draws":195,"losses":33,"wins":12},"GB2-05":{"draws":0,"losses":289,"wins":125},"GB2-06":{"draws":24,"losses":363,"wins":65},"GB2-07":{"draws":0,"losses":246,"wins":284},"GB2-08":{"draws":230,"losses":253,"wins":19}},"per_game_match_totals_tracks":{"medium":{"GB2-03":{"draws":68,"losses":60,"wins":26},"GB2-05":{"draws":0,"losses":162,"wins":50},"GB2-06":{"draws":21,"losses":190,"wins":31},"GB2-07":{"draws":0,"losses":164,"wins":96},"GB2-08":{"draws":31,"losses":198,"wins":19}},"none":{"GB2-02":{"draws":175,"losses":41,"wins":6},"GB2-03":{"draws":89,"losses":39,"wins":16},"GB2-04":{"draws":195,"losses":33,"wins":12},"GB2-05":{"draws":0,"losses":127,"wins":75},"GB2-06":{"draws":3,"losses":173,"wins":34},"GB2-07":{"draws":0,"losses":82,"wins":188},"GB2-08":{"draws":199,"losses":55,"wins":0}}},"per_game_raw_elo_tracks":{"medium":{"GB2-03":1348.526619811048,"GB2-05":1047.7461247257522,"GB2-06":1061.3788853371843,"GB2-07":1221.9849749023533,"GB2-08":1000.1996922567068},"none":{"GB2-02":1355.284192320307,"GB2-03":1377.2044232021271,"GB2-04":1435.7803501103617,"GB2-05":1258.620863230517,"GB2-06":942.5334712146507,"GB2-07":1760.9349440620415,"GB2-08":1318.7216823557662}},"per_game_tracks":{"medium":{"GB2-03":22.81853039406397,"GB2-05":20.687011705599502,"GB2-06":24.059984646529276,"GB2-07":28.39953999096173,"GB2-08":0.0},"none":{"GB2-02":0.10631171802151808,"GB2-03":25.41165252574357,"GB2-04":16.483548530056492,"GB2-05":33.9241439224965,"GB2-06":16.768455567867043,"GB2-07":64.55194498926986,"GB2-08":24.208092923512243}},"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":17.065270226169293,"none":21.082076264331786},"reasoning_agg":{"medium":{"max":28.39953999096173,"mean":17.065270226169293,"min":0.0},"none":{"max":64.55194498926986,"mean":21.082076264331786,"min":0.10631171802151808}},"reasoning_labels":{"highest":"Setting not tested","medium":"Reasoning enabled","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":64.55194498926986,"reasoning_variance":4.016806038162493},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":28.39953999096173,"expected_score":15.760537599114903,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-1.3047326270543902},"none":{"ceiling_score":64.55194498926986,"expected_score":24.388339088008784,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":3.306262823676999}}},{"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":0.04706874999999999}},"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":0.081084},"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":0.04706875},"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":0.21994025}},"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":0.34809300000000004},"codegen_latency_ms":{"attempt_count":37,"max_ms":98448,"mean_ms":43627.1875,"min_ms":14244,"run_count":16},"codegen_latency_ms_by_reasoning":{"highest":{"attempt_count":19,"max_ms":98448,"mean_ms":63383.0,"min_ms":47134,"run_count":8},"medium":{"attempt_count":18,"max_ms":33720,"mean_ms":23871.375,"min_ms":14244,"run_count":8}},"codegen_output_tokens":{"attempt_count":37,"output_max":22966,"output_mean":9375.1875,"output_min":1329,"run_count":16},"codegen_output_tokens_by_reasoning":{"highest":{"attempt_count":19,"output_max":22966,"output_mean":14948.625,"output_min":10673,"run_count":8},"medium":{"attempt_count":18,"output_max":5938,"output_mean":3801.75,"output_min":1329,"run_count":8}},"display_name":"Gemini 3.1 Flash Lite","economics":{"all":18.854419621586167,"highest":21.107450358093807,"medium":20.300581815650165,"none":14.858192619973412},"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":"2026-09-25T12:16:54Z","match_totals_all":{"draws":914,"losses":1993,"wins":626},"match_totals_tracks":{"highest":{"draws":310,"losses":614,"wins":195},"medium":{"draws":371,"losses":773,"wins":290},"none":{"draws":233,"losses":606,"wins":141}},"model_slug":"google-gemini-3-1-flash-lite","overall":{"max":32.38410669171022,"mean":16.956767089532573,"min":0.08310002118024254},"overall_eligibility_flag":false,"overall_ineligibility_reason_codes":["untested_or_ineligible_settings"],"overall_official_rank":71,"overall_ranking_status":"partial","per_game":{"GB2-04":15.135889350399117,"GB2-05":14.9868688465287,"GB2-06":24.574609551117437,"GB2-07":29.827400148127907,"GB2-08":21.012483894295887},"per_game_all":{"GB2-05":17.48299640798731,"GB2-06":27.66911854877432,"GB2-07":11.411143907996868},"per_game_match_totals_all":{"GB2-01":{"draws":169,"losses":217,"wins":60},"GB2-02":{"draws":182,"losses":17,"wins":1},"GB2-04":{"draws":317,"losses":75,"wins":46},"GB2-05":{"draws":0,"losses":442,"wins":124},"GB2-06":{"draws":6,"losses":456,"wins":205},"GB2-07":{"draws":0,"losses":567,"wins":111},"GB2-08":{"draws":240,"losses":219,"wins":79}},"per_game_match_totals_tracks":{"highest":{"GB2-04":{"draws":153,"losses":44,"wins":17},"GB2-05":{"draws":0,"losses":155,"wins":37},"GB2-06":{"draws":0,"losses":161,"wins":52},"GB2-07":{"draws":0,"losses":167,"wins":77},"GB2-08":{"draws":157,"losses":87,"wins":12}},"medium":{"GB2-01":{"draws":123,"losses":88,"wins":39},"GB2-04":{"draws":164,"losses":31,"wins":29},"GB2-05":{"draws":0,"losses":144,"wins":58},"GB2-06":{"draws":1,"losses":166,"wins":75},"GB2-07":{"draws":0,"losses":212,"wins":22},"GB2-08":{"draws":83,"losses":132,"wins":67}},"none":{"GB2-01":{"draws":46,"losses":129,"wins":21},"GB2-02":{"draws":182,"losses":17,"wins":1},"GB2-05":{"draws":0,"losses":143,"wins":29},"GB2-06":{"draws":5,"losses":129,"wins":78},"GB2-07":{"draws":0,"losses":188,"wins":12}}},"per_game_raw_elo_all":{"GB2-05":998.5511519717874,"GB2-06":1122.2773312476927,"GB2-07":970.3713166549347},"per_game_raw_elo_tracks":{"highest":{"GB2-04":1428.365696951213,"GB2-05":958.6120200971899,"GB2-06":1071.5827214437497,"GB2-07":1244.08501176749,"GB2-08":1276.5376688345202},"medium":{"GB2-01":1310.2844110489343,"GB2-04":1436.2297377289594,"GB2-05":1091.2531945362703,"GB2-06":1094.304139623621,"GB2-07":864.0842697939028,"GB2-08":1278.7602474587914},"none":{"GB2-01":1149.1878789322218,"GB2-02":1421.0571705946704,"GB2-05":945.7882412819017,"GB2-06":1200.9451326757076,"GB2-07":802.9446684034115}},"per_game_tracks":{"highest":{"GB2-04":15.135889350399117,"GB2-05":14.9868688465287,"GB2-06":24.574609551117437,"GB2-07":29.827400148127907,"GB2-08":21.012483894295887},"medium":{"GB2-01":30.361355618251846,"GB2-04":16.41547033342719,"GB2-05":23.38472503344923,"GB2-06":26.048639403495315,"GB2-07":4.322931554682457,"GB2-08":21.27036895059496},"none":{"GB2-01":18.578517458993726,"GB2-02":9.167843583998868,"GB2-05":14.077395343984001,"GB2-06":32.38410669171022,"GB2-07":0.08310002118024254}},"provider_color":"#4285F4","provider_company":"Google","provider_key":"google","provider_text_color":"#f5f9ff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":18.767472185108453,"medium":18.891820080243768,"none":13.211009003245497},"reasoning_agg":{"highest":{"max":29.827400148127907,"mean":18.767472185108453,"min":14.9868688465287},"medium":{"max":30.361355618251846,"mean":18.891820080243768,"min":4.322931554682457},"none":{"max":32.38410669171022,"mean":13.211009003245497,"min":0.08310002118024254}},"reasoning_labels":{"highest":"High","medium":"Medium","none":"Reasoning disabled"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":32.38410669171022,"expected_score":12.1230162528444,"reasoning_variance":5.680811076998271,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-4.833750836688173},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":29.827400148127907,"expected_score":8.396864239134635,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-10.370607945973818},"medium":{"ceiling_score":30.361355618251846,"expected_score":18.699220328799466,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-0.19259975144430186},"none":{"ceiling_score":32.38410669171022,"expected_score":13.620283010215095,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.40927400696959815}}},{"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":21.516338854208463,"none":18.550407116525978},"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":1867,"losses":2320,"wins":861},"match_totals_tracks":{"medium":{"draws":706,"losses":1299,"wins":537},"none":{"draws":1161,"losses":1021,"wins":324}},"model_slug":"inclusionai-ling-3-0-flash","overall":{"max":38.44617773407611,"mean":16.802608996281997,"min":2.780537548479402},"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":72,"overall_ranking_status":"partial","per_game_match_totals_all":{"GB2-01":{"draws":242,"losses":479,"wins":165},"GB2-02":{"draws":512,"losses":113,"wins":9},"GB2-03":{"draws":137,"losses":191,"wins":52},"GB2-04":{"draws":528,"losses":95,"wins":45},"GB2-06":{"draws":11,"losses":736,"wins":177},"GB2-07":{"draws":0,"losses":565,"wins":385},"GB2-08":{"draws":437,"losses":141,"wins":28}},"per_game_match_totals_tracks":{"medium":{"GB2-01":{"draws":101,"losses":265,"wins":20},"GB2-02":{"draws":294,"losses":74,"wins":4},"GB2-04":{"draws":307,"losses":67,"wins":28},"GB2-06":{"draws":4,"losses":328,"wins":100},"GB2-07":{"draws":0,"losses":565,"wins":385}},"none":{"GB2-01":{"draws":141,"losses":214,"wins":145},"GB2-02":{"draws":218,"losses":39,"wins":5},"GB2-03":{"draws":137,"losses":191,"wins":52},"GB2-04":{"draws":221,"losses":28,"wins":17},"GB2-06":{"draws":7,"losses":408,"wins":77},"GB2-08":{"draws":437,"losses":141,"wins":28}}},"per_game_raw_elo_tracks":{"medium":{"GB2-01":1227.4780847101188,"GB2-02":1406.579899262466,"GB2-04":1418.1586600442279,"GB2-06":1206.8396642184798,"GB2-07":1387.6214948670254},"none":{"GB2-01":1388.4078953975363,"GB2-02":1434.756171592916,"GB2-03":1231.463984346276,"GB2-04":1432.8613262957322,"GB2-06":851.2838770926161,"GB2-08":1313.988025781403}},"per_game_tracks":{"medium":{"GB2-01":22.81526569038575,"GB2-02":2.780537548479402,"GB2-04":11.520265373967671,"GB2-06":32.0194479241334,"GB2-07":38.44617773407611},"none":{"GB2-01":35.962389688777634,"GB2-02":11.596795030322259,"GB2-03":12.11442709036542,"GB2-04":16.237152166315024,"GB2-06":11.38300416268924,"GB2-08":24.0086745606863}},"provider_color":"#1677FF","provider_company":"InclusionAI","provider_key":"inclusionai","provider_text_color":"#f8fbff","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"medium":17.111314480985172,"none":16.493903511578825},"reasoning_agg":{"medium":{"max":38.44617773407611,"mean":17.111314480985172,"min":2.780537548479402},"none":{"max":35.962389688777634,"mean":16.493903511578825,"min":11.38300416268924}},"reasoning_labels":{"highest":"Setting not tested","medium":"Enabled","none":"None"},"reasoning_settings":{},"score_diagnostics":{"ceiling_score":38.44617773407611,"reasoning_variance":0.6174109694063468},"score_diagnostics_by_reasoning":{"medium":{"ceiling_score":38.44617773407611,"expected_score":19.644079984660664,"reliability_score":77.82846544227553,"uncertainty_avg":22.17153455772447,"uncertainty_penalty":2.532765503675492},"none":{"ceiling_score":35.962389688777634,"expected_score":17.415515339253783,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":0.9216118276749583}}},{"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":0.05924464000000001},"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":0.01440924},"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":0.09619379999999998},"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":20.205129732851056,"medium":11.70214905886831},"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":"2026-09-25T14:28:45Z","match_totals_all":{"draws":377,"losses":403,"wins":18},"match_totals_tracks":{"highest":{"draws":178,"losses":68,"wins":6},"medium":{"draws":199,"losses":335,"wins":12}},"model_slug":"ibm-granite-granite-4-2-8b","overall":{"max":22.686800313770597,"mean":10.144355486455655,"min":0.7174978039660215},"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":20.205129732851056},"per_game_match_totals_all":{"GB2-03":{"draws":178,"losses":68,"wins":6},"GB2-07":{"draws":0,"losses":260,"wins":12},"GB2-08":{"draws":199,"losses":75,"wins":0}},"per_game_match_totals_tracks":{"highest":{"GB2-03":{"draws":178,"losses":68,"wins":6}},"medium":{"GB2-07":{"draws":0,"losses":260,"wins":12},"GB2-08":{"draws":199,"losses":75,"wins":0}}},"per_game_raw_elo_tracks":{"highest":{"GB2-03":1313.7415020745286},"medium":{"GB2-07":808.4054617383549,"GB2-08":1297.7581063353189}},"per_game_tracks":{"highest":{"GB2-03":20.205129732851056},"medium":{"GB2-07":0.7174978039660215,"GB2-08":22.686800313770597}},"provider_color":"#7DB0FF","provider_company":"Other","provider_key":"other","provider_text_color":"#081019","rank_movement":null,"rank_movement_baseline_at":null,"reasoning":{"highest":12.014042018929752,"medium":8.274668953981557},"reasoning_agg":{"highest":{"max":20.205129732851056,"mean":12.014042018929752,"min":20.205129732851056},"medium":{"max":22.686800313770597,"mean":8.274668953981557,"min":0.7174978039660215}},"reasoning_labels":{"highest":"Full","medium":"Low","none":"Setting not tested"},"reasoning_settings":{"balanced":"low","intensive":"high"},"score_diagnostics":{"ceiling_score":22.686800313770597,"reasoning_variance":3.739373064948195},"score_diagnostics_by_reasoning":{"highest":{"ceiling_score":20.205129732851056,"expected_score":2.919479095054425,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":-9.094562923875326},"medium":{"ceiling_score":22.686800313770597,"expected_score":12.872624064671529,"reliability_score":100.0,"uncertainty_avg":0.0,"uncertainty_penalty":4.597955110689972}}}],"public_release_id":"gb2-20260925-719069527ef4","results_cut_id":"gb2-20260925-719069527ef4","schema_version":2,"snapshot_id":"20260925_163935","suite_line_id":"gamebench2","suite_version":"2-known8-r3","version_display":"2026-09-25 16:39 UTC","versus_totals_all":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":32,"losses":34,"wins":34},"claude-fable-5":{"draws":20,"losses":54,"wins":16},"claude-fable-5-1":{"draws":4,"losses":86,"wins":4},"claude-opus-4-5":{"draws":41,"losses":70,"wins":27},"claude-opus-4-8":{"draws":6,"losses":9,"wins":7},"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":70,"wins":24},"cohere/north-mini-code":{"draws":7,"losses":5,"wins":4},"deepseek/deepseek-v4-flash":{"draws":49,"losses":60,"wins":33},"deepseek/deepseek-v4-pro":{"draws":38,"losses":59,"wins":35},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":50,"wins":31},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":9,"wins":6},"google/gemini-3.1-flash-lite":{"draws":11,"losses":7,"wins":18},"google/gemini-3.5-flash":{"draws":41,"losses":56,"wins":27},"google/gemini-3.5-flash-lite":{"draws":86,"losses":79,"wins":87},"google/gemini-3.6-flash":{"draws":58,"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":32,"wins":24},"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":14,"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":57,"wins":10},"gpt-6-luna":{"draws":1,"losses":5,"wins":8},"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":28,"wins":34},"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":34,"wins":45},"meta/muse-spark-1.2":{"draws":25,"losses":31,"wins":24},"meta/muse-spark-1.3":{"draws":23,"losses":46,"wins":19},"minimax/minimax-m3":{"draws":4,"losses":8,"wins":20},"mistralai/mistral-medium-3-5":{"draws":36,"losses":19,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":7,"wins":1},"moonshotai/kimi-k3":{"draws":28,"losses":45,"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":23,"losses":67,"wins":42},"openai/gpt-oss-120b":{"draws":49,"losses":36,"wins":43},"poolside/laguna-s-2.1":{"draws":43,"losses":23,"wins":30},"qwen/qwen3.7-max":{"draws":5,"losses":9,"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":34,"wins":20},"qwen/qwen3.8-flash":{"draws":36,"losses":35,"wins":19},"qwen/qwen3.8-max":{"draws":47,"losses":47,"wins":44},"qwen/qwen3.8-max-0902":{"draws":7,"losses":9,"wins":2},"stealth/ox-alpha":{"draws":98,"losses":194,"wins":86},"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":64,"wins":21},"thinkingmachines/inkling":{"draws":40,"losses":34,"wins":54},"thinkingmachines/inkling-small":{"draws":56,"losses":27,"wins":55},"x-ai/grok-4.5":{"draws":31,"losses":57,"wins":14},"x-ai/grok-4.6":{"draws":35,"losses":48,"wins":19},"x-ai/grok-4.7":{"draws":0,"losses":8,"wins":6},"x-ai/grok-build-0.1":{"draws":3,"losses":2,"wins":7},"xiaomi/mimo-v2.5":{"draws":19,"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":12,"wins":7},"z-ai/glm-5.2":{"draws":78,"losses":49,"wins":53},"z-ai/glm-5.3":{"draws":25,"losses":56,"wins":13},"z-ai/glm-5.3-flash":{"draws":35,"losses":53,"wins":16},"z-ai/glm-5.3-flashx":{"draws":3,"losses":13,"wins":2}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":16,"wins":54},"claude-fable-5":{"draws":12,"losses":42,"wins":42},"claude-fable-5-1":{"draws":5,"losses":135,"wins":28},"claude-opus-4-5":{"draws":25,"losses":16,"wins":99},"claude-opus-4-8":{"draws":7,"losses":8,"wins":15},"claude-opus-5":{"draws":11,"losses":76,"wins":27},"claude-opus-5-5":{"draws":2,"losses":14,"wins":2},"claude-sonnet-5":{"draws":35,"losses":24,"wins":85},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":29,"losses":13,"wins":90},"deepseek/deepseek-v4-pro":{"draws":24,"losses":33,"wins":61},"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":28,"wins":91},"google/gemini-3.5-flash-lite":{"draws":39,"losses":31,"wins":136},"google/gemini-3.6-flash":{"draws":39,"losses":65,"wins":104},"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":12},"gpt-5.4-nano":{"draws":3,"losses":7,"wins":28},"gpt-5.5":{"draws":6,"losses":11,"wins":17},"gpt-5.6-luna":{"draws":31,"losses":20,"wins":51},"gpt-5.6-sol":{"draws":21,"losses":68,"wins":73},"gpt-5.6-terra":{"draws":38,"losses":22,"wins":82},"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":31},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":17},"meituan/longcat-2.0":{"draws":11,"losses":20,"wins":42},"meta/muse-glimmer-30b":{"draws":25,"losses":8,"wins":37},"meta/muse-spark-1.2":{"draws":18,"losses":22,"wins":46},"meta/muse-spark-1.3":{"draws":20,"losses":43,"wins":63},"minimax/minimax-m3":{"draws":5,"losses":2,"wins":15},"mistralai/mistral-medium-3-5":{"draws":22,"losses":8,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":26,"losses":20,"wins":82},"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":9,"losses":20,"wins":101},"openai/gpt-oss-120b":{"draws":28,"losses":11,"wins":51},"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":61},"qwen/qwen3.8-27b":{"draws":10,"losses":17,"wins":43},"qwen/qwen3.8-flash":{"draws":29,"losses":13,"wins":42},"qwen/qwen3.8-max":{"draws":21,"losses":39,"wins":72},"qwen/qwen3.8-max-0902":{"draws":8,"losses":4,"wins":14},"stealth/ox-alpha":{"draws":100,"losses":101,"wins":255},"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":81},"thinkingmachines/inkling":{"draws":18,"losses":2,"wins":56},"thinkingmachines/inkling-small":{"draws":28,"losses":12,"wins":62},"x-ai/grok-4.5":{"draws":16,"losses":38,"wins":52},"x-ai/grok-4.6":{"draws":39,"losses":54,"wins":75},"x-ai/grok-4.7":{"draws":1,"losses":12,"wins":9},"x-ai/grok-build-0.1":{"draws":2,"losses":4,"wins":10},"xiaomi/mimo-v2.5":{"draws":13,"losses":2,"wins":43},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":3,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":13},"z-ai/glm-5.2":{"draws":45,"losses":28,"wins":73},"z-ai/glm-5.3":{"draws":22,"losses":77,"wins":53},"z-ai/glm-5.3-flash":{"draws":25,"losses":44,"wins":73},"z-ai/glm-5.3-flashx":{"draws":6,"losses":11,"wins":9}},"claude-fable-5-1":{"bytedance-seed/seed-2.0-code":{"draws":4,"losses":4,"wins":86},"claude-fable-5":{"draws":5,"losses":28,"wins":135},"claude-fable-5-1":{"draws":10,"losses":81,"wins":81},"claude-opus-4-5":{"draws":5,"losses":3,"wins":142},"claude-opus-4-8":{"draws":2,"losses":5,"wins":21},"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":156},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":6,"losses":1,"wins":111},"deepseek/deepseek-v4-pro":{"draws":8,"losses":3,"wins":115},"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":24},"google/gemini-3.5-flash":{"draws":14,"losses":10,"wins":130},"google/gemini-3.5-flash-lite":{"draws":15,"losses":1,"wins":166},"google/gemini-3.6-flash":{"draws":12,"losses":23,"wins":191},"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":42},"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":20},"gpt-5.5":{"draws":4,"losses":5,"wins":33},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":80},"gpt-5.6-sol":{"draws":17,"losses":27,"wins":140},"gpt-5.6-terra":{"draws":13,"losses":3,"wins":124},"gpt-6-astra":{"draws":18,"losses":109,"wins":65},"gpt-6-luna":{"draws":1,"losses":0,"wins":15},"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":36},"meituan/longcat-2.0":{"draws":1,"losses":3,"wins":48},"meta/muse-glimmer-30b":{"draws":6,"losses":0,"wins":58},"meta/muse-spark-1.2":{"draws":10,"losses":9,"wins":93},"meta/muse-spark-1.3":{"draws":4,"losses":7,"wins":127},"minimax/minimax-m3":{"draws":1,"losses":1,"wins":16},"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":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":36},"o3":{"draws":0,"losses":6,"wins":116},"openai/gpt-oss-120b":{"draws":7,"losses":1,"wins":62},"poolside/laguna-s-2.1":{"draws":5,"losses":0,"wins":69},"qwen/qwen3.7-max":{"draws":1,"losses":0,"wins":21},"qwen/qwen3.7-plus":{"draws":3,"losses":0,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":8,"wins":133},"qwen/qwen3.8-27b":{"draws":3,"losses":1,"wins":68},"qwen/qwen3.8-flash":{"draws":5,"losses":4,"wins":77},"qwen/qwen3.8-max":{"draws":6,"losses":5,"wins":137},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":23},"stealth/ox-alpha":{"draws":51,"losses":27,"wins":474},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":20},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":26},"tencent/hy4-preview":{"draws":5,"losses":14,"wins":127},"thinkingmachines/inkling":{"draws":7,"losses":0,"wins":71},"thinkingmachines/inkling-small":{"draws":8,"losses":1,"wins":109},"x-ai/grok-4.5":{"draws":1,"losses":10,"wins":95},"x-ai/grok-4.6":{"draws":11,"losses":24,"wins":147},"x-ai/grok-4.7":{"draws":1,"losses":0,"wins":15},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":18},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":62},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":5,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":13},"z-ai/glm-5.2":{"draws":16,"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":3,"wins":33}},"claude-opus-4-5":{"bytedance-seed/seed-2.0-code":{"draws":29,"losses":21,"wins":60},"claude-fable-5":{"draws":23,"losses":82,"wins":15},"claude-fable-5-1":{"draws":4,"losses":129,"wins":3},"claude-opus-4-5":{"draws":59,"losses":50,"wins":61},"claude-opus-4-8":{"draws":31,"losses":64,"wins":29},"claude-opus-5":{"draws":37,"losses":189,"wins":26},"claude-opus-5-5":{"draws":4,"losses":28,"wins":2},"claude-sonnet-5":{"draws":71,"losses":41,"wins":102},"cohere/north-mini-code":{"draws":8,"losses":9,"wins":33},"deepseek/deepseek-v4-flash":{"draws":33,"losses":35,"wins":64},"deepseek/deepseek-v4-pro":{"draws":22,"losses":36,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":43,"wins":37},"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":57,"wins":43},"google/gemini-3.5-flash-lite":{"draws":156,"losses":105,"wins":215},"google/gemini-3.6-flash":{"draws":107,"losses":192,"wins":147},"google/gemini-3.8-flash":{"draws":30,"losses":60,"wins":24},"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":25,"losses":16,"wins":19},"gpt-5.4":{"draws":52,"losses":103,"wins":37},"gpt-5.4-mini":{"draws":36,"losses":20,"wins":26},"gpt-5.4-nano":{"draws":27,"losses":30,"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":106,"wins":4},"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":33,"wins":93},"meta/muse-glimmer-30b":{"draws":28,"losses":13,"wins":47},"meta/muse-spark-1.2":{"draws":35,"losses":67,"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":42,"losses":88,"wins":194},"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":42,"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":38,"losses":61,"wins":30},"qwen/qwen3.8-max-0902":{"draws":4,"losses":9,"wins":1},"stealth/ox-alpha":{"draws":115,"losses":154,"wins":116},"stepfun/step-3.7-flash":{"draws":18,"losses":15,"wins":53},"tencent/hy3-preview":{"draws":23,"losses":16,"wins":25},"tencent/hy4-preview":{"draws":30,"losses":52,"wins":36},"thinkingmachines/inkling":{"draws":65,"losses":28,"wins":107},"thinkingmachines/inkling-small":{"draws":34,"losses":15,"wins":58},"x-ai/grok-4.5":{"draws":77,"losses":106,"wins":65},"x-ai/grok-4.6":{"draws":33,"losses":63,"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":28,"wins":77},"xiaomi/mimo-v2.5-pro":{"draws":13,"losses":32,"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":27,"losses":52,"wins":35},"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":7,"wins":9},"claude-fable-5":{"draws":7,"losses":15,"wins":8},"claude-fable-5-1":{"draws":2,"losses":21,"wins":5},"claude-opus-4-5":{"draws":49,"losses":45,"wins":112},"claude-opus-4-8":{"draws":24,"losses":38,"wins":38},"claude-opus-5":{"draws":49,"losses":155,"wins":54},"claude-opus-5-5":{"draws":0,"losses":27,"wins":3},"claude-sonnet-5":{"draws":11,"losses":4,"wins":13},"cohere/north-mini-code":{"draws":14,"losses":4,"wins":56},"deepseek/deepseek-v4-flash":{"draws":35,"losses":4,"wins":47},"deepseek/deepseek-v4-pro":{"draws":8,"losses":15,"wins":17},"deepseek/deepseek-v4-pro-0813":{"draws":6,"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":66},"google/gemini-3.5-flash":{"draws":34,"losses":12,"wins":32},"google/gemini-3.5-flash-lite":{"draws":34,"losses":16,"wins":56},"google/gemini-3.6-flash":{"draws":32,"losses":59,"wins":45},"google/gemini-3.8-flash":{"draws":6,"losses":14,"wins":16},"google/gemma-4-31b-it":{"draws":29,"losses":5,"wins":36},"gpt-4.1":{"draws":18,"losses":6,"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":41,"wins":1},"gpt-6-luna":{"draws":2,"losses":3,"wins":5},"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":16},"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":8,"losses":5,"wins":15},"meta/muse-spark-1.2":{"draws":13,"losses":11,"wins":22},"meta/muse-spark-1.3":{"draws":9,"losses":14,"wins":15},"minimax/minimax-m3":{"draws":22,"losses":12,"wins":42},"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":27,"wins":16},"nex-agi/nex-n2-pro":{"draws":31,"losses":8,"wins":39},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":15,"wins":66},"o3":{"draws":9,"losses":25,"wins":72},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":6},"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":9,"losses":8,"wins":11},"qwen/qwen3.8-max":{"draws":14,"losses":15,"wins":19},"qwen/qwen3.8-max-0902":{"draws":10,"losses":11,"wins":3},"stealth/ox-alpha":{"draws":35,"losses":60,"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":25,"wins":19},"thinkingmachines/inkling":{"draws":24,"losses":17,"wins":65},"thinkingmachines/inkling-small":{"draws":8,"losses":2,"wins":16},"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":7,"wins":5},"x-ai/grok-build-0.1":{"draws":18,"losses":10,"wins":32},"xiaomi/mimo-v2.5":{"draws":69,"losses":21,"wins":116},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":22,"wins":38},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":8,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":8},"z-ai/glm-5.2":{"draws":66,"losses":53,"wins":91},"z-ai/glm-5.3":{"draws":8,"losses":19,"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":76},"claude-fable-5-1":{"draws":10,"losses":37,"wins":27},"claude-opus-4-5":{"draws":60,"losses":50,"wins":302},"claude-opus-4-8":{"draws":49,"losses":54,"wins":155},"claude-opus-5":{"draws":82,"losses":291,"wins":291},"claude-opus-5-5":{"draws":4,"losses":25,"wins":11},"claude-sonnet-5":{"draws":11,"losses":16,"wins":53},"cohere/north-mini-code":{"draws":6,"losses":5,"wins":45},"deepseek/deepseek-v4-flash":{"draws":19,"losses":10,"wins":103},"deepseek/deepseek-v4-pro":{"draws":5,"losses":6,"wins":43},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":9,"wins":38},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":9,"wins":17},"google/gemini-3.1-flash-lite":{"draws":19,"losses":4,"wins":67},"google/gemini-3.5-flash":{"draws":16,"losses":13,"wins":95},"google/gemini-3.5-flash-lite":{"draws":31,"losses":20,"wins":197},"google/gemini-3.6-flash":{"draws":36,"losses":48,"wins":182},"google/gemini-3.8-flash":{"draws":17,"losses":26,"wins":71},"google/gemma-4-31b-it":{"draws":14,"losses":11,"wins":57},"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":140},"gpt-5.4":{"draws":4,"losses":5,"wins":51},"gpt-5.4-mini":{"draws":27,"losses":10,"wins":85},"gpt-5.4-nano":{"draws":26,"losses":24,"wins":160},"gpt-5.5":{"draws":35,"losses":77,"wins":168},"gpt-5.6-luna":{"draws":8,"losses":10,"wins":56},"gpt-5.6-sol":{"draws":15,"losses":15,"wins":78},"gpt-5.6-terra":{"draws":11,"losses":2,"wins":49},"gpt-6-astra":{"draws":10,"losses":51,"wins":19},"gpt-6-luna":{"draws":4,"losses":1,"wins":29},"gpt-6-sol":{"draws":7,"losses":15,"wins":18},"ibm-granite/granite-4.2-8b":{"draws":0,"losses":0,"wins":6},"inception/mercury-2.5-preview":{"draws":9,"losses":1,"wins":28},"inclusionai/ling-3.0-flash":{"draws":25,"losses":5,"wins":66},"meituan/longcat-2.0":{"draws":20,"losses":20,"wins":148},"meta/muse-glimmer-30b":{"draws":5,"losses":6,"wins":35},"meta/muse-spark-1.2":{"draws":4,"losses":10,"wins":40},"meta/muse-spark-1.3":{"draws":16,"losses":14,"wins":64},"minimax/minimax-m3":{"draws":12,"losses":10,"wins":86},"mistralai/mistral-medium-3-5":{"draws":9,"losses":4,"wins":23},"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":157},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":52},"poolside/laguna-s-2.1":{"draws":17,"losses":16,"wins":179},"qwen/qwen3.7-max":{"draws":17,"losses":17,"wins":104},"qwen/qwen3.7-plus":{"draws":14,"losses":10,"wins":44},"qwen/qwen3.8-2.4t-a95b":{"draws":14,"losses":15,"wins":53},"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":11,"losses":9,"wins":50},"qwen/qwen3.8-max-0902":{"draws":9,"losses":12,"wins":21},"stealth/ox-alpha":{"draws":36,"losses":35,"wins":198},"stepfun/step-3.7-flash":{"draws":11,"losses":1,"wins":66},"tencent/hy3-preview":{"draws":21,"losses":10,"wins":95},"tencent/hy4-preview":{"draws":9,"losses":10,"wins":63},"thinkingmachines/inkling":{"draws":15,"losses":21,"wins":146},"thinkingmachines/inkling-small":{"draws":3,"losses":4,"wins":45},"x-ai/grok-4.5":{"draws":33,"losses":45,"wins":148},"x-ai/grok-4.6":{"draws":9,"losses":15,"wins":57},"x-ai/grok-4.7":{"draws":3,"losses":8,"wins":13},"x-ai/grok-build-0.1":{"draws":10,"losses":5,"wins":37},"xiaomi/mimo-v2.5":{"draws":48,"losses":16,"wins":196},"xiaomi/mimo-v2.5-pro":{"draws":17,"losses":6,"wins":81},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":2,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":5,"wins":6},"z-ai/glm-5.2":{"draws":53,"losses":22,"wins":179},"z-ai/glm-5.3":{"draws":15,"losses":20,"wins":47},"z-ai/glm-5.3-flash":{"draws":8,"losses":20,"wins":76},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":24}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":12},"claude-fable-5":{"draws":2,"losses":2,"wins":14},"claude-fable-5-1":{"draws":5,"losses":15,"wins":18},"claude-opus-4-5":{"draws":4,"losses":3,"wins":41},"claude-opus-4-8":{"draws":0,"losses":3,"wins":27},"claude-opus-5":{"draws":4,"losses":11,"wins":25},"claude-opus-5-5":{"draws":8,"losses":58,"wins":58},"claude-sonnet-5":{"draws":1,"losses":2,"wins":11},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":21},"deepseek/deepseek-v4-flash":{"draws":0,"losses":1,"wins":23},"deepseek/deepseek-v4-pro":{"draws":1,"losses":0,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":31},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":22},"google/gemini-3.5-flash":{"draws":1,"losses":3,"wins":24},"google/gemini-3.5-flash-lite":{"draws":5,"losses":0,"wins":33},"google/gemini-3.6-flash":{"draws":4,"losses":0,"wins":34},"google/gemini-3.8-flash":{"draws":4,"losses":2,"wins":18},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":10},"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":16},"gpt-5.4":{"draws":2,"losses":3,"wins":19},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":16},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":20},"gpt-5.5":{"draws":0,"losses":4,"wins":14},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":9},"gpt-5.6-sol":{"draws":1,"losses":2,"wins":17},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":20},"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":26},"meta/muse-spark-1.2":{"draws":0,"losses":2,"wins":12},"meta/muse-spark-1.3":{"draws":0,"losses":2,"wins":16},"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":17},"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":27},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":31},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":26},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":20},"qwen/qwen3.7-plus":{"draws":1,"losses":0,"wins":5},"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":27},"stealth/ox-alpha":{"draws":8,"losses":4,"wins":86},"stepfun/step-3.7-flash":{"draws":2,"losses":0,"wins":20},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":22},"tencent/hy4-preview":{"draws":0,"losses":3,"wins":13},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":26},"thinkingmachines/inkling-small":{"draws":6,"losses":0,"wins":18},"x-ai/grok-4.5":{"draws":4,"losses":7,"wins":33},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":26},"x-ai/grok-4.7":{"draws":4,"losses":19,"wins":61},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":6},"xiaomi/mimo-v2.5":{"draws":4,"losses":0,"wins":40},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":1,"wins":51},"xiaomi/mimo-v2.6-pro":{"draws":15,"losses":11,"wins":48},"z-ai/glm-5.2":{"draws":3,"losses":2,"wins":51},"z-ai/glm-5.3":{"draws":1,"losses":4,"wins":21},"z-ai/glm-5.3-flash":{"draws":6,"losses":0,"wins":26},"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":70},"claude-fable-5":{"draws":35,"losses":85,"wins":24},"claude-fable-5-1":{"draws":11,"losses":156,"wins":5},"claude-opus-4-5":{"draws":79,"losses":110,"wins":53},"claude-opus-4-8":{"draws":11,"losses":13,"wins":4},"claude-opus-5":{"draws":11,"losses":53,"wins":16},"claude-opus-5-5":{"draws":1,"losses":11,"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":62,"losses":34,"wins":78},"deepseek/deepseek-v4-pro":{"draws":48,"losses":44,"wins":40},"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":12,"losses":3,"wins":27},"google/gemini-3.5-flash":{"draws":48,"losses":61,"wins":43},"google/gemini-3.5-flash-lite":{"draws":144,"losses":117,"wins":261},"google/gemini-3.6-flash":{"draws":112,"losses":189,"wins":145},"google/gemini-3.8-flash":{"draws":38,"losses":71,"wins":35},"google/gemma-4-31b-it":{"draws":8,"losses":2,"wins":12},"gpt-4.1":{"draws":3,"losses":1,"wins":2},"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":7,"wins":11},"gpt-5.4-nano":{"draws":6,"losses":14,"wins":10},"gpt-5.5":{"draws":11,"losses":18,"wins":3},"gpt-5.6-luna":{"draws":99,"losses":80,"wins":115},"gpt-5.6-sol":{"draws":48,"losses":232,"wins":43},"gpt-5.6-terra":{"draws":49,"losses":53,"wins":38},"gpt-6-astra":{"draws":7,"losses":131,"wins":10},"gpt-6-luna":{"draws":2,"losses":6,"wins":6},"gpt-6-sol":{"draws":2,"losses":28,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":12},"inception/mercury-2.5-preview":{"draws":49,"losses":9,"wins":52},"inclusionai/ling-3.0-flash":{"draws":28,"losses":12,"wins":64},"meituan/longcat-2.0":{"draws":53,"losses":16,"wins":87},"meta/muse-glimmer-30b":{"draws":49,"losses":16,"wins":57},"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":86,"losses":112,"wins":58},"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":133,"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":18},"qwen/qwen3.7-plus":{"draws":8,"losses":4,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":59,"losses":51,"wins":36},"qwen/qwen3.8-27b":{"draws":19,"losses":25,"wins":26},"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":120,"losses":204,"wins":139},"stepfun/step-3.7-flash":{"draws":9,"losses":21,"wins":32},"tencent/hy3-preview":{"draws":15,"losses":9,"wins":14},"tencent/hy4-preview":{"draws":46,"losses":59,"wins":35},"thinkingmachines/inkling":{"draws":64,"losses":26,"wins":110},"thinkingmachines/inkling-small":{"draws":47,"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":7,"losses":9,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":8,"wins":5},"z-ai/glm-5.2":{"draws":62,"losses":54,"wins":78},"z-ai/glm-5.3":{"draws":25,"losses":105,"wins":16},"z-ai/glm-5.3-flash":{"draws":31,"losses":76,"wins":37},"z-ai/glm-5.3-flashx":{"draws":9,"losses":3,"wins":8}},"cohere/north-mini-code":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":4,"wins":5},"claude-fable-5":{"draws":2,"losses":14,"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":31,"losses":14,"wins":13},"google/gemini-3.6-flash":{"draws":27,"losses":49,"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":18,"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":12,"wins":0},"gpt-6-luna":{"draws":1,"losses":3,"wins":0},"gpt-6-sol":{"draws":3,"losses":6,"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":1,"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":23,"losses":23,"wins":16},"openai/gpt-oss-120b":{"draws":6,"losses":5,"wins":1},"poolside/laguna-s-2.1":{"draws":37,"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":14,"wins":1},"qwen/qwen3.8-max-0902":{"draws":1,"losses":12,"wins":1},"stealth/ox-alpha":{"draws":10,"losses":35,"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":15,"losses":22,"wins":25},"thinkingmachines/inkling-small":{"draws":10,"losses":8,"wins":2},"x-ai/grok-4.5":{"draws":9,"losses":31,"wins":4},"x-ai/grok-4.6":{"draws":8,"losses":8,"wins":0},"x-ai/grok-4.7":{"draws":1,"losses":5,"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":6,"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":111,"wins":1},"claude-opus-4-5":{"draws":61,"losses":84,"wins":45},"claude-opus-4-8":{"draws":35,"losses":47,"wins":4},"claude-opus-5":{"draws":19,"losses":103,"wins":10},"claude-opus-5-5":{"draws":0,"losses":23,"wins":1},"claude-sonnet-5":{"draws":62,"losses":78,"wins":34},"cohere/north-mini-code":{"draws":23,"losses":17,"wins":22},"deepseek/deepseek-v4-flash":{"draws":42,"losses":69,"wins":69},"deepseek/deepseek-v4-pro":{"draws":51,"losses":68,"wins":29},"deepseek/deepseek-v4-pro-0813":{"draws":52,"losses":60,"wins":34},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":40,"wins":5},"google/gemini-3.1-flash-lite":{"draws":26,"losses":37,"wins":63},"google/gemini-3.5-flash":{"draws":53,"losses":59,"wins":36},"google/gemini-3.5-flash-lite":{"draws":106,"losses":91,"wins":105},"google/gemini-3.6-flash":{"draws":81,"losses":146,"wins":51},"google/gemini-3.8-flash":{"draws":32,"losses":88,"wins":20},"google/gemma-4-31b-it":{"draws":17,"losses":20,"wins":33},"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":68,"wins":23},"gpt-5.4-mini":{"draws":41,"losses":26,"wins":17},"gpt-5.4-nano":{"draws":33,"losses":36,"wins":45},"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":96,"wins":19},"gpt-5.6-terra":{"draws":60,"losses":63,"wins":31},"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":32,"wins":39},"meituan/longcat-2.0":{"draws":53,"losses":31,"wins":50},"meta/muse-glimmer-30b":{"draws":76,"losses":27,"wins":49},"meta/muse-spark-1.2":{"draws":22,"losses":43,"wins":19},"meta/muse-spark-1.3":{"draws":36,"losses":75,"wins":25},"minimax/minimax-m3":{"draws":32,"losses":30,"wins":30},"mistralai/mistral-medium-3-5":{"draws":37,"losses":16,"wins":31},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":14,"wins":10},"moonshotai/kimi-k3":{"draws":49,"losses":58,"wins":39},"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":68,"losses":34,"wins":42},"qwen/qwen3.7-max":{"draws":28,"losses":22,"wins":14},"qwen/qwen3.7-plus":{"draws":25,"losses":28,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":53,"losses":72,"wins":31},"qwen/qwen3.8-27b":{"draws":19,"losses":44,"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":26,"wins":4},"stealth/ox-alpha":{"draws":152,"losses":203,"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":54},"thinkingmachines/inkling-small":{"draws":83,"losses":24,"wins":67},"x-ai/grok-4.5":{"draws":29,"losses":69,"wins":24},"x-ai/grok-4.6":{"draws":47,"losses":94,"wins":17},"x-ai/grok-4.7":{"draws":2,"losses":21,"wins":1},"x-ai/grok-build-0.1":{"draws":20,"losses":13,"wins":15},"xiaomi/mimo-v2.5":{"draws":93,"losses":83,"wins":58},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":26,"wins":19},"xiaomi/mimo-v2.6-flash":{"draws":11,"losses":18,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":2},"z-ai/glm-5.2":{"draws":101,"losses":103,"wins":60},"z-ai/glm-5.3":{"draws":36,"losses":73,"wins":7},"z-ai/glm-5.3-flash":{"draws":40,"losses":56,"wins":26},"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":59},"claude-fable-5":{"draws":24,"losses":61,"wins":33},"claude-fable-5-1":{"draws":8,"losses":115,"wins":3},"claude-opus-4-5":{"draws":28,"losses":38,"wins":46},"claude-opus-4-8":{"draws":8,"losses":17,"wins":15},"claude-opus-5":{"draws":5,"losses":43,"wins":6},"claude-opus-5-5":{"draws":1,"losses":23,"wins":0},"claude-sonnet-5":{"draws":48,"losses":40,"wins":44},"cohere/north-mini-code":{"draws":6,"losses":2,"wins":10},"deepseek/deepseek-v4-flash":{"draws":51,"losses":29,"wins":68},"deepseek/deepseek-v4-pro":{"draws":28,"losses":32,"wins":32},"deepseek/deepseek-v4-pro-0813":{"draws":50,"losses":49,"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":48,"wins":53},"google/gemini-3.5-flash-lite":{"draws":83,"losses":61,"wins":118},"google/gemini-3.6-flash":{"draws":58,"losses":80,"wins":78},"google/gemini-3.8-flash":{"draws":41,"losses":66,"wins":25},"google/gemma-4-31b-it":{"draws":1,"losses":2,"wins":11},"gpt-4.1":{"draws":1,"losses":0,"wins":5},"gpt-4.1-nano":{"draws":2,"losses":5,"wins":1},"gpt-5":{"draws":19,"losses":10,"wins":11},"gpt-5.4":{"draws":42,"losses":51,"wins":33},"gpt-5.4-mini":{"draws":5,"losses":4,"wins":7},"gpt-5.4-nano":{"draws":9,"losses":3,"wins":22},"gpt-5.5":{"draws":7,"losses":21,"wins":8},"gpt-5.6-luna":{"draws":45,"losses":29,"wins":48},"gpt-5.6-sol":{"draws":13,"losses":67,"wins":34},"gpt-5.6-terra":{"draws":44,"losses":35,"wins":49},"gpt-6-astra":{"draws":4,"losses":86,"wins":12},"gpt-6-luna":{"draws":4,"losses":16,"wins":2},"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":49,"wins":37},"minimax/minimax-m3":{"draws":4,"losses":1,"wins":5},"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":2,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":12},"o3":{"draws":27,"losses":46,"wins":75},"openai/gpt-oss-120b":{"draws":44,"losses":26,"wins":44},"poolside/laguna-s-2.1":{"draws":34,"losses":24,"wins":34},"qwen/qwen3.7-max":{"draws":6,"losses":6,"wins":10},"qwen/qwen3.7-plus":{"draws":10,"losses":1,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":43,"losses":54,"wins":35},"qwen/qwen3.8-27b":{"draws":15,"losses":35,"wins":26},"qwen/qwen3.8-flash":{"draws":26,"losses":30,"wins":30},"qwen/qwen3.8-max":{"draws":36,"losses":53,"wins":37},"qwen/qwen3.8-max-0902":{"draws":2,"losses":6,"wins":2},"stealth/ox-alpha":{"draws":130,"losses":153,"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":34,"losses":13,"wins":45},"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":35,"losses":60,"wins":33},"x-ai/grok-4.7":{"draws":2,"losses":10,"wins":4},"x-ai/grok-build-0.1":{"draws":5,"losses":4,"wins":11},"xiaomi/mimo-v2.5":{"draws":18,"losses":6,"wins":20},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":9,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":2,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":3,"wins":1},"z-ai/glm-5.2":{"draws":58,"losses":59,"wins":63},"z-ai/glm-5.3":{"draws":23,"losses":73,"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":37,"losses":31,"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":40,"wins":49},"claude-opus-4-8":{"draws":6,"losses":16,"wins":16},"claude-opus-5":{"draws":7,"losses":38,"wins":9},"claude-opus-5-5":{"draws":0,"losses":22,"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":52,"losses":34,"wins":60},"deepseek/deepseek-v4-pro":{"draws":50,"losses":41,"wins":49},"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":64,"wins":41},"google/gemini-3.5-flash-lite":{"draws":87,"losses":48,"wins":91},"google/gemini-3.6-flash":{"draws":71,"losses":101,"wins":66},"google/gemini-3.8-flash":{"draws":36,"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":3,"wins":1},"gpt-5":{"draws":20,"losses":10,"wins":20},"gpt-5.4":{"draws":44,"losses":45,"wins":31},"gpt-5.4-mini":{"draws":11,"losses":4,"wins":5},"gpt-5.4-nano":{"draws":3,"losses":9,"wins":16},"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":74,"wins":28},"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":6},"gpt-6-sol":{"draws":2,"losses":14,"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":52,"losses":19,"wins":53},"meta/muse-spark-1.2":{"draws":31,"losses":35,"wins":32},"meta/muse-spark-1.3":{"draws":30,"losses":58,"wins":30},"minimax/minimax-m3":{"draws":4,"losses":3,"wins":13},"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":7,"losses":4,"wins":11},"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":20,"wins":30},"poolside/laguna-s-2.1":{"draws":41,"losses":18,"wins":31},"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":40,"wins":46},"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":45,"losses":40,"wins":37},"qwen/qwen3.8-max-0902":{"draws":9,"losses":2,"wins":5},"stealth/ox-alpha":{"draws":129,"losses":169,"wins":140},"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":49,"losses":24,"wins":65},"x-ai/grok-4.5":{"draws":26,"losses":33,"wins":35},"x-ai/grok-4.6":{"draws":53,"losses":55,"wins":36},"x-ai/grok-4.7":{"draws":0,"losses":10,"wins":2},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":27,"losses":10,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":8,"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":58,"losses":51,"wins":71},"z-ai/glm-5.3":{"draws":26,"losses":65,"wins":25},"z-ai/glm-5.3-flash":{"draws":37,"losses":55,"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":7,"losses":6,"wins":9},"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":17,"wins":9},"claude-opus-5-5":{"draws":0,"losses":31,"wins":1},"claude-sonnet-5":{"draws":12,"losses":5,"wins":9},"cohere/north-mini-code":{"draws":2,"losses":2,"wins":18},"deepseek/deepseek-v4-flash":{"draws":13,"losses":5,"wins":40},"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":5},"gpt-4.1":{"draws":5,"losses":5,"wins":12},"gpt-5":{"draws":8,"losses":7,"wins":7},"gpt-5.4":{"draws":13,"losses":20,"wins":7},"gpt-5.4-mini":{"draws":9,"losses":7,"wins":6},"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":7},"gpt-6-astra":{"draws":4,"losses":26,"wins":2},"gpt-6-luna":{"draws":18,"losses":8,"wins":12},"gpt-6-sol":{"draws":13,"losses":19,"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":11,"losses":2,"wins":17},"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":8,"losses":6,"wins":6},"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":6,"wins":17},"openai/gpt-oss-120b":{"draws":9,"losses":7,"wins":18},"poolside/laguna-s-2.1":{"draws":7,"losses":3,"wins":2},"qwen/qwen3.7-max":{"draws":7,"losses":5,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"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":7,"wins":12},"qwen/qwen3.8-max-0902":{"draws":15,"losses":16,"wins":17},"stealth/ox-alpha":{"draws":20,"losses":48,"wins":34},"stepfun/step-3.7-flash":{"draws":5,"losses":2,"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":2,"wins":14},"x-ai/grok-4.5":{"draws":5,"losses":10,"wins":1},"x-ai/grok-4.6":{"draws":13,"losses":13,"wins":6},"x-ai/grok-4.7":{"draws":4,"losses":6,"wins":4},"x-ai/grok-build-0.1":{"draws":4,"losses":0,"wins":12},"xiaomi/mimo-v2.5":{"draws":18,"losses":2,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":3,"wins":6},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":6,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":4},"z-ai/glm-5.2":{"draws":11,"losses":14,"wins":19},"z-ai/glm-5.3":{"draws":9,"losses":13,"wins":8},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"wins":11},"z-ai/glm-5.3-flashx":{"draws":14,"losses":19,"wins":9}},"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":24,"wins":0},"claude-opus-4-5":{"draws":35,"losses":89,"wins":8},"claude-opus-4-8":{"draws":25,"losses":66,"wins":5},"claude-opus-5":{"draws":19,"losses":67,"wins":4},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":12,"losses":27,"wins":3},"cohere/north-mini-code":{"draws":15,"losses":32,"wins":27},"deepseek/deepseek-v4-flash":{"draws":26,"losses":63,"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":41,"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":4,"losses":25,"wins":1},"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":33,"wins":6},"gpt-6-astra":{"draws":0,"losses":24,"wins":0},"gpt-6-luna":{"draws":5,"losses":12,"wins":3},"gpt-6-sol":{"draws":4,"losses":18,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":12,"losses":4,"wins":2},"inclusionai/ling-3.0-flash":{"draws":19,"losses":17,"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":4,"losses":14,"wins":0},"minimax/minimax-m3":{"draws":20,"losses":32,"wins":30},"mistralai/mistral-medium-3-5":{"draws":6,"losses":6,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":12,"losses":23,"wins":3},"moonshotai/kimi-k3":{"draws":5,"losses":15,"wins":2},"nex-agi/nex-n2-pro":{"draws":14,"losses":27,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":38,"losses":42,"wins":27},"o3":{"draws":12,"losses":59,"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":28,"wins":12},"qwen/qwen3.7-plus":{"draws":17,"losses":31,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":12,"wins":0},"qwen/qwen3.8-27b":{"draws":7,"losses":17,"wins":4},"qwen/qwen3.8-flash":{"draws":14,"losses":4,"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":35,"wins":8},"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":16,"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":38,"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":38,"losses":73,"wins":19},"z-ai/glm-5.3":{"draws":5,"losses":16,"wins":1},"z-ai/glm-5.3-flash":{"draws":1,"losses":13,"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":27,"wins":56},"claude-fable-5":{"draws":31,"losses":91,"wins":28},"claude-fable-5-1":{"draws":14,"losses":130,"wins":10},"claude-opus-4-5":{"draws":39,"losses":54,"wins":77},"claude-opus-4-8":{"draws":34,"losses":32,"wins":12},"claude-opus-5":{"draws":16,"losses":95,"wins":13},"claude-opus-5-5":{"draws":1,"losses":24,"wins":3},"claude-sonnet-5":{"draws":48,"losses":43,"wins":61},"cohere/north-mini-code":{"draws":12,"losses":7,"wins":17},"deepseek/deepseek-v4-flash":{"draws":53,"losses":36,"wins":59},"deepseek/deepseek-v4-pro":{"draws":39,"losses":53,"wins":48},"deepseek/deepseek-v4-pro-0813":{"draws":51,"losses":41,"wins":64},"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":34,"wins":34},"google/gemini-3.5-flash-lite":{"draws":84,"losses":73,"wins":119},"google/gemini-3.6-flash":{"draws":57,"losses":82,"wins":89},"google/gemini-3.8-flash":{"draws":36,"losses":75,"wins":45},"google/gemma-4-31b-it":{"draws":10,"losses":2,"wins":10},"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":7,"wins":21},"gpt-5.4-nano":{"draws":19,"losses":16,"wins":45},"gpt-5.5":{"draws":17,"losses":19,"wins":12},"gpt-5.6-luna":{"draws":55,"losses":31,"wins":48},"gpt-5.6-sol":{"draws":21,"losses":90,"wins":43},"gpt-5.6-terra":{"draws":47,"losses":51,"wins":40},"gpt-6-astra":{"draws":18,"losses":124,"wins":6},"gpt-6-luna":{"draws":7,"losses":12,"wins":17},"gpt-6-sol":{"draws":7,"losses":20,"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":30},"meituan/longcat-2.0":{"draws":26,"losses":21,"wins":71},"meta/muse-glimmer-30b":{"draws":36,"losses":27,"wins":51},"meta/muse-spark-1.2":{"draws":25,"losses":36,"wins":49},"meta/muse-spark-1.3":{"draws":23,"losses":69,"wins":40},"minimax/minimax-m3":{"draws":16,"losses":10,"wins":14},"mistralai/mistral-medium-3-5":{"draws":22,"losses":13,"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":8,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":20,"losses":8,"wins":12},"o3":{"draws":23,"losses":49,"wins":92},"openai/gpt-oss-120b":{"draws":43,"losses":25,"wins":54},"poolside/laguna-s-2.1":{"draws":40,"losses":20,"wins":46},"qwen/qwen3.7-max":{"draws":18,"losses":14,"wins":12},"qwen/qwen3.7-plus":{"draws":13,"losses":3,"wins":12},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":55,"wins":50},"qwen/qwen3.8-27b":{"draws":21,"losses":39,"wins":24},"qwen/qwen3.8-flash":{"draws":41,"losses":23,"wins":42},"qwen/qwen3.8-max":{"draws":48,"losses":33,"wins":51},"qwen/qwen3.8-max-0902":{"draws":8,"losses":7,"wins":7},"stealth/ox-alpha":{"draws":115,"losses":190,"wins":174},"stepfun/step-3.7-flash":{"draws":13,"losses":13,"wins":28},"tencent/hy3-preview":{"draws":8,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":32,"losses":77,"wins":45},"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":48,"wins":35},"x-ai/grok-4.6":{"draws":39,"losses":70,"wins":33},"x-ai/grok-4.7":{"draws":0,"losses":16,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":1,"wins":14},"xiaomi/mimo-v2.5":{"draws":24,"losses":17,"wins":29},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":19,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":7,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":66,"losses":72,"wins":72},"z-ai/glm-5.3":{"draws":25,"losses":82,"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":86,"losses":87,"wins":79},"claude-fable-5":{"draws":39,"losses":136,"wins":31},"claude-fable-5-1":{"draws":15,"losses":166,"wins":1},"claude-opus-4-5":{"draws":175,"losses":231,"wins":116},"claude-opus-4-8":{"draws":34,"losses":56,"wins":16},"claude-opus-5":{"draws":31,"losses":197,"wins":20},"claude-opus-5-5":{"draws":5,"losses":33,"wins":0},"claude-sonnet-5":{"draws":144,"losses":261,"wins":117},"cohere/north-mini-code":{"draws":31,"losses":13,"wins":14},"deepseek/deepseek-v4-flash":{"draws":106,"losses":105,"wins":91},"deepseek/deepseek-v4-pro":{"draws":83,"losses":118,"wins":61},"deepseek/deepseek-v4-pro-0813":{"draws":87,"losses":91,"wins":48},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":30,"wins":16},"google/gemini-3.1-flash-lite":{"draws":30,"losses":21,"wins":41},"google/gemini-3.5-flash":{"draws":84,"losses":119,"wins":73},"google/gemini-3.5-flash-lite":{"draws":332,"losses":344,"wins":344},"google/gemini-3.6-flash":{"draws":337,"losses":475,"wins":209},"google/gemini-3.8-flash":{"draws":46,"losses":137,"wins":11},"google/gemma-4-31b-it":{"draws":16,"losses":24,"wins":20},"gpt-4.1":{"draws":15,"losses":12,"wins":17},"gpt-4.1-nano":{"draws":3,"losses":17,"wins":14},"gpt-5":{"draws":39,"losses":29,"wins":20},"gpt-5.4":{"draws":133,"losses":260,"wins":65},"gpt-5.4-mini":{"draws":30,"losses":38,"wins":24},"gpt-5.4-nano":{"draws":33,"losses":31,"wins":54},"gpt-5.5":{"draws":49,"losses":30,"wins":11},"gpt-5.6-luna":{"draws":169,"losses":200,"wins":159},"gpt-5.6-sol":{"draws":70,"losses":355,"wins":41},"gpt-5.6-terra":{"draws":74,"losses":108,"wins":52},"gpt-6-astra":{"draws":13,"losses":152,"wins":1},"gpt-6-luna":{"draws":10,"losses":24,"wins":8},"gpt-6-sol":{"draws":9,"losses":48,"wins":7},"ibm-granite/granite-4.2-8b":{"draws":25,"losses":0,"wins":9},"inception/mercury-2.5-preview":{"draws":96,"losses":36,"wins":78},"inclusionai/ling-3.0-flash":{"draws":92,"losses":47,"wins":123},"meituan/longcat-2.0":{"draws":111,"losses":153,"wins":176},"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":108,"wins":44},"minimax/minimax-m3":{"draws":21,"losses":22,"wins":25},"mistralai/mistral-medium-3-5":{"draws":60,"losses":34,"wins":66},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":5,"wins":9},"moonshotai/kimi-k3":{"draws":190,"losses":260,"wins":108},"nex-agi/nex-n2-pro":{"draws":25,"losses":8,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":41,"losses":26,"wins":33},"o3":{"draws":111,"losses":378,"wins":229},"openai/gpt-oss-120b":{"draws":86,"losses":73,"wins":83},"poolside/laguna-s-2.1":{"draws":192,"losses":139,"wins":117},"qwen/qwen3.7-max":{"draws":25,"losses":12,"wins":27},"qwen/qwen3.7-plus":{"draws":23,"losses":12,"wins":17},"qwen/qwen3.8-2.4t-a95b":{"draws":77,"losses":111,"wins":40},"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":202,"losses":375,"wins":166},"stepfun/step-3.7-flash":{"draws":44,"losses":70,"wins":58},"tencent/hy3-preview":{"draws":31,"losses":22,"wins":9},"tencent/hy4-preview":{"draws":80,"losses":106,"wins":46},"thinkingmachines/inkling":{"draws":183,"losses":127,"wins":196},"thinkingmachines/inkling-small":{"draws":107,"losses":91,"wins":102},"x-ai/grok-4.5":{"draws":122,"losses":254,"wins":96},"x-ai/grok-4.6":{"draws":71,"losses":120,"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":53,"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":111,"wins":102},"z-ai/glm-5.3":{"draws":44,"losses":151,"wins":17},"z-ai/glm-5.3-flash":{"draws":65,"losses":117,"wins":40},"z-ai/glm-5.3-flashx":{"draws":7,"losses":28,"wins":5}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":58,"losses":51,"wins":89},"claude-fable-5":{"draws":39,"losses":104,"wins":65},"claude-fable-5-1":{"draws":12,"losses":191,"wins":23},"claude-opus-4-5":{"draws":126,"losses":164,"wins":204},"claude-opus-4-8":{"draws":32,"losses":45,"wins":59},"claude-opus-5":{"draws":36,"losses":182,"wins":48},"claude-opus-5-5":{"draws":4,"losses":34,"wins":0},"claude-sonnet-5":{"draws":112,"losses":145,"wins":189},"cohere/north-mini-code":{"draws":27,"losses":12,"wins":49},"deepseek/deepseek-v4-flash":{"draws":81,"losses":51,"wins":146},"deepseek/deepseek-v4-pro":{"draws":58,"losses":78,"wins":80},"deepseek/deepseek-v4-pro-0813":{"draws":71,"losses":66,"wins":101},"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":57,"losses":89,"wins":82},"google/gemini-3.5-flash-lite":{"draws":337,"losses":209,"wins":475},"google/gemini-3.6-flash":{"draws":172,"losses":304,"wins":304},"google/gemini-3.8-flash":{"draws":45,"losses":97,"wins":79},"google/gemma-4-31b-it":{"draws":14,"losses":13,"wins":21},"gpt-4.1":{"draws":17,"losses":11,"wins":26},"gpt-4.1-nano":{"draws":14,"losses":10,"wins":4},"gpt-5":{"draws":25,"losses":41,"wins":46},"gpt-5.4":{"draws":110,"losses":196,"wins":130},"gpt-5.4-mini":{"draws":30,"losses":19,"wins":44},"gpt-5.4-nano":{"draws":35,"losses":30,"wins":47},"gpt-5.5":{"draws":47,"losses":44,"wins":49},"gpt-5.6-luna":{"draws":134,"losses":107,"wins":211},"gpt-5.6-sol":{"draws":60,"losses":237,"wins":133},"gpt-5.6-terra":{"draws":66,"losses":60,"wins":88},"gpt-6-astra":{"draws":20,"losses":162,"wins":14},"gpt-6-luna":{"draws":13,"losses":7,"wins":30},"gpt-6-sol":{"draws":7,"losses":38,"wins":11},"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":116,"losses":39,"wins":109},"meituan/longcat-2.0":{"draws":115,"losses":71,"wins":203},"meta/muse-glimmer-30b":{"draws":88,"losses":30,"wins":94},"meta/muse-spark-1.2":{"draws":64,"losses":152,"wins":130},"meta/muse-spark-1.3":{"draws":36,"losses":93,"wins":71},"minimax/minimax-m3":{"draws":15,"losses":10,"wins":39},"mistralai/mistral-medium-3-5":{"draws":44,"losses":18,"wins":54},"moonshotai/kimi-k2.7-code":{"draws":6,"losses":4,"wins":18},"moonshotai/kimi-k3":{"draws":155,"losses":175,"wins":214},"nex-agi/nex-n2-pro":{"draws":17,"losses":12,"wins":39},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":31,"losses":9,"wins":52},"o3":{"draws":110,"losses":219,"wins":327},"openai/gpt-oss-120b":{"draws":72,"losses":29,"wins":81},"poolside/laguna-s-2.1":{"draws":167,"losses":61,"wins":154},"qwen/qwen3.7-max":{"draws":15,"losses":11,"wins":42},"qwen/qwen3.7-plus":{"draws":21,"losses":12,"wins":41},"qwen/qwen3.8-2.4t-a95b":{"draws":64,"losses":76,"wins":100},"qwen/qwen3.8-27b":{"draws":33,"losses":38,"wins":67},"qwen/qwen3.8-flash":{"draws":64,"losses":39,"wins":59},"qwen/qwen3.8-max":{"draws":68,"losses":88,"wins":93},"qwen/qwen3.8-max-0902":{"draws":14,"losses":8,"wins":16},"stealth/ox-alpha":{"draws":171,"losses":283,"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":93,"wins":105},"thinkingmachines/inkling":{"draws":167,"losses":72,"wins":237},"thinkingmachines/inkling-small":{"draws":74,"losses":50,"wins":100},"x-ai/grok-4.5":{"draws":98,"losses":190,"wins":206},"x-ai/grok-4.6":{"draws":59,"losses":87,"wins":68},"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":21,"losses":22,"wins":33},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":14,"wins":17},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":9,"wins":10},"z-ai/glm-5.2":{"draws":91,"losses":87,"wins":120},"z-ai/glm-5.3":{"draws":33,"losses":136,"wins":43},"z-ai/glm-5.3-flash":{"draws":54,"losses":96,"wins":70},"z-ai/glm-5.3-flashx":{"draws":15,"losses":12,"wins":13}},"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":42,"losses":30,"wins":66},"claude-opus-4-8":{"draws":6,"losses":16,"wins":14},"claude-opus-5":{"draws":17,"losses":71,"wins":26},"claude-opus-5-5":{"draws":4,"losses":18,"wins":2},"claude-sonnet-5":{"draws":38,"losses":35,"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":41,"losses":25,"wins":66},"deepseek/deepseek-v4-pro-0813":{"draws":36,"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":137},"google/gemini-3.6-flash":{"draws":45,"losses":79,"wins":97},"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":5,"losses":8,"wins":15},"gpt-5.4-nano":{"draws":7,"losses":6,"wins":23},"gpt-5.5":{"draws":8,"losses":15,"wins":9},"gpt-5.6-luna":{"draws":33,"losses":30,"wins":65},"gpt-5.6-sol":{"draws":20,"losses":79,"wins":59},"gpt-5.6-terra":{"draws":47,"losses":33,"wins":54},"gpt-6-astra":{"draws":19,"losses":134,"wins":11},"gpt-6-luna":{"draws":6,"losses":4,"wins":8},"gpt-6-sol":{"draws":2,"losses":12,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":3,"losses":0,"wins":11},"inception/mercury-2.5-preview":{"draws":33,"losses":2,"wins":37},"inclusionai/ling-3.0-flash":{"draws":11,"losses":2,"wins":33},"meituan/longcat-2.0":{"draws":19,"losses":10,"wins":36},"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":30},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":4},"moonshotai/kimi-k3":{"draws":47,"losses":31,"wins":60},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":11},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":4,"wins":15},"o3":{"draws":18,"losses":40,"wins":90},"openai/gpt-oss-120b":{"draws":25,"losses":8,"wins":57},"poolside/laguna-s-2.1":{"draws":26,"losses":8,"wins":52},"qwen/qwen3.7-max":{"draws":4,"losses":9,"wins":13},"qwen/qwen3.7-plus":{"draws":6,"losses":0,"wins":16},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":50,"wins":66},"qwen/qwen3.8-27b":{"draws":19,"losses":30,"wins":51},"qwen/qwen3.8-flash":{"draws":24,"losses":21,"wins":47},"qwen/qwen3.8-max":{"draws":39,"losses":43,"wins":54},"qwen/qwen3.8-max-0902":{"draws":6,"losses":1,"wins":7},"stealth/ox-alpha":{"draws":113,"losses":155,"wins":216},"stepfun/step-3.7-flash":{"draws":10,"losses":1,"wins":23},"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":47,"losses":16,"wins":55},"x-ai/grok-4.5":{"draws":22,"losses":61,"wins":35},"x-ai/grok-4.6":{"draws":43,"losses":54,"wins":51},"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":24,"losses":6,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":6,"wins":15},"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":8,"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":36,"wins":5},"claude-opus-5":{"draws":14,"losses":57,"wins":11},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":8,"losses":12,"wins":2},"cohere/north-mini-code":{"draws":11,"losses":10,"wins":17},"deepseek/deepseek-v4-flash":{"draws":17,"losses":33,"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":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":22,"losses":27,"wins":33},"google/gemini-3.5-flash":{"draws":10,"losses":10,"wins":2},"google/gemini-3.5-flash-lite":{"draws":16,"losses":20,"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":2,"losses":8,"wins":2},"gpt-5.4-mini":{"draws":7,"losses":19,"wins":16},"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":12,"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":32,"wins":5},"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":3},"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":36,"wins":5},"stepfun/step-3.7-flash":{"draws":4,"losses":26,"wins":4},"tencent/hy3-preview":{"draws":16,"losses":19,"wins":7},"tencent/hy4-preview":{"draws":4,"losses":11,"wins":1},"thinkingmachines/inkling":{"draws":12,"losses":19,"wins":15},"thinkingmachines/inkling-small":{"draws":3,"losses":7,"wins":4},"x-ai/grok-4.5":{"draws":4,"losses":16,"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":17,"wins":7},"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":28,"losses":24,"wins":12},"z-ai/glm-5.3":{"draws":1,"losses":12,"wins":1},"z-ai/glm-5.3-flash":{"draws":2,"losses":16,"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":18,"losses":24,"wins":6},"claude-opus-5":{"draws":12,"losses":70,"wins":7},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":3,"losses":2,"wins":1},"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":1,"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":17,"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":8,"losses":3,"wins":3},"gpt-6-astra":{"draws":4,"losses":10,"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":9,"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":10,"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":38,"losses":20,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":3,"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":0},"z-ai/glm-5.3-flashx":{"draws":8,"losses":7,"wins":3}},"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":3},"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":14,"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":3,"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":42,"wins":1},"claude-opus-4-5":{"draws":46,"losses":38,"wins":40},"claude-opus-4-8":{"draws":23,"losses":56,"wins":27},"claude-opus-5":{"draws":24,"losses":140,"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":19,"losses":11,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":20,"losses":20,"wins":10},"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":39,"losses":20,"wins":29},"google/gemini-3.6-flash":{"draws":25,"losses":46,"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":20,"losses":22,"wins":22},"gpt-5.4":{"draws":11,"losses":18,"wins":11},"gpt-5.4-mini":{"draws":30,"losses":23,"wins":21},"gpt-5.4-nano":{"draws":17,"losses":30,"wins":43},"gpt-5.5":{"draws":31,"losses":61,"wins":32},"gpt-5.6-luna":{"draws":3,"losses":6,"wins":17},"gpt-5.6-sol":{"draws":2,"losses":17,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":9,"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":20,"wins":21},"meituan/longcat-2.0":{"draws":34,"losses":22,"wins":44},"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":7,"losses":7,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":10,"wins":10},"moonshotai/kimi-k3":{"draws":18,"losses":15,"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":52},"openai/gpt-oss-120b":{"draws":10,"losses":4,"wins":10},"poolside/laguna-s-2.1":{"draws":26,"losses":30,"wins":24},"qwen/qwen3.7-max":{"draws":27,"losses":14,"wins":25},"qwen/qwen3.7-plus":{"draws":14,"losses":9,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":14,"wins":10},"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":11,"wins":5},"qwen/qwen3.8-max-0902":{"draws":8,"losses":7,"wins":5},"stealth/ox-alpha":{"draws":34,"losses":56,"wins":30},"stepfun/step-3.7-flash":{"draws":23,"losses":5,"wins":28},"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":40},"thinkingmachines/inkling-small":{"draws":10,"losses":2,"wins":16},"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":19,"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":48},"z-ai/glm-5.3":{"draws":5,"losses":22,"wins":3},"z-ai/glm-5.3-flash":{"draws":18,"losses":16,"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":24,"wins":32},"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":41,"wins":111},"claude-opus-4-8":{"draws":5,"losses":13,"wins":10},"claude-opus-5":{"draws":4,"losses":51,"wins":5},"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":68},"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":13,"losses":7,"wins":20},"google/gemini-3.1-flash-lite":{"draws":4,"losses":1,"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":110,"losses":130,"wins":196},"google/gemini-3.8-flash":{"draws":40,"losses":57,"wins":61},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":8},"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":11,"wins":20},"gpt-5.5":{"draws":16,"losses":15,"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":107,"wins":19},"gpt-6-luna":{"draws":8,"losses":3,"wins":11},"gpt-6-sol":{"draws":3,"losses":16,"wins":5},"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":74},"meta/muse-glimmer-30b":{"draws":34,"losses":18,"wins":38},"meta/muse-spark-1.2":{"draws":38,"losses":66,"wins":94},"meta/muse-spark-1.3":{"draws":24,"losses":44,"wins":46},"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":0,"losses":0,"wins":8},"moonshotai/kimi-k3":{"draws":63,"losses":60,"wins":133},"nex-agi/nex-n2-pro":{"draws":3,"losses":2,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":1,"wins":15},"o3":{"draws":30,"losses":55,"wins":185},"openai/gpt-oss-120b":{"draws":58,"losses":15,"wins":39},"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":17},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":60,"wins":50},"qwen/qwen3.8-27b":{"draws":21,"losses":15,"wins":36},"qwen/qwen3.8-flash":{"draws":22,"losses":26,"wins":28},"qwen/qwen3.8-max":{"draws":41,"losses":49,"wins":50},"qwen/qwen3.8-max-0902":{"draws":9,"losses":10,"wins":21},"stealth/ox-alpha":{"draws":146,"losses":134,"wins":171},"stepfun/step-3.7-flash":{"draws":13,"losses":8,"wins":39},"tencent/hy3-preview":{"draws":14,"losses":9,"wins":9},"tencent/hy4-preview":{"draws":30,"losses":41,"wins":49},"thinkingmachines/inkling":{"draws":41,"losses":29,"wins":80},"thinkingmachines/inkling-small":{"draws":59,"losses":11,"wins":39},"x-ai/grok-4.5":{"draws":51,"losses":69,"wins":91},"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":3},"xiaomi/mimo-v2.5":{"draws":18,"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":71,"wins":56},"z-ai/glm-5.3-flash":{"draws":31,"losses":45,"wins":56},"z-ai/glm-5.3-flashx":{"draws":7,"losses":7,"wins":4}},"gpt-5.4-mini":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":10,"wins":6},"claude-fable-5":{"draws":9,"losses":12,"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":0,"losses":16,"wins":0},"claude-sonnet-5":{"draws":10,"losses":11,"wins":7},"cohere/north-mini-code":{"draws":18,"losses":7,"wins":23},"deepseek/deepseek-v4-flash":{"draws":41,"losses":17,"wins":26},"deepseek/deepseek-v4-pro":{"draws":5,"losses":7,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":11,"losses":5,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":6,"wins":7},"google/gemini-3.1-flash-lite":{"draws":19,"losses":11,"wins":34},"google/gemini-3.5-flash":{"draws":14,"losses":21,"wins":7},"google/gemini-3.5-flash-lite":{"draws":30,"losses":24,"wins":38},"google/gemini-3.6-flash":{"draws":30,"losses":44,"wins":19},"google/gemini-3.8-flash":{"draws":5,"losses":15,"wins":8},"google/gemma-4-31b-it":{"draws":7,"losses":16,"wins":19},"gpt-4.1":{"draws":20,"losses":5,"wins":19},"gpt-5":{"draws":30,"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":41,"losses":57,"wins":30},"gpt-5.5":{"draws":49,"losses":35,"wins":8},"gpt-5.6-luna":{"draws":4,"losses":6,"wins":2},"gpt-5.6-sol":{"draws":10,"losses":19,"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":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":4},"inclusionai/ling-3.0-flash":{"draws":32,"losses":8,"wins":20},"meituan/longcat-2.0":{"draws":39,"losses":29,"wins":40},"meta/muse-glimmer-30b":{"draws":13,"losses":3,"wins":8},"meta/muse-spark-1.2":{"draws":2,"losses":9,"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":54,"losses":25,"wins":27},"o3":{"draws":10,"losses":22,"wins":20},"openai/gpt-oss-120b":{"draws":6,"losses":6,"wins":6},"poolside/laguna-s-2.1":{"draws":43,"losses":16,"wins":23},"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":5,"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":11,"wins":11},"tencent/hy4-preview":{"draws":11,"losses":15,"wins":8},"thinkingmachines/inkling":{"draws":29,"losses":21,"wins":20},"thinkingmachines/inkling-small":{"draws":12,"losses":5,"wins":3},"x-ai/grok-4.5":{"draws":19,"losses":26,"wins":5},"x-ai/grok-4.6":{"draws":7,"losses":21,"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":51},"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":40,"wins":17},"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":20,"wins":0},"claude-opus-4-5":{"draws":55,"losses":92,"wins":69},"claude-opus-4-8":{"draws":35,"losses":86,"wins":35},"claude-opus-5":{"draws":26,"losses":160,"wins":24},"claude-opus-5-5":{"draws":0,"losses":20,"wins":0},"claude-sonnet-5":{"draws":6,"losses":10,"wins":14},"cohere/north-mini-code":{"draws":24,"losses":21,"wins":43},"deepseek/deepseek-v4-flash":{"draws":33,"losses":45,"wins":36},"deepseek/deepseek-v4-pro":{"draws":9,"losses":22,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":16,"wins":9},"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":16},"google/gemini-3.5-flash-lite":{"draws":33,"losses":54,"wins":31},"google/gemini-3.6-flash":{"draws":35,"losses":47,"wins":30},"google/gemini-3.8-flash":{"draws":7,"losses":23,"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":43,"wins":30},"gpt-5.4":{"draws":5,"losses":20,"wins":11},"gpt-5.4-mini":{"draws":41,"losses":30,"wins":57},"gpt-5.4-nano":{"draws":38,"losses":63,"wins":63},"gpt-5.5":{"draws":47,"losses":73,"wins":44},"gpt-5.6-luna":{"draws":14,"losses":15,"wins":19},"gpt-5.6-sol":{"draws":5,"losses":30,"wins":3},"gpt-5.6-terra":{"draws":9,"losses":17,"wins":14},"gpt-6-astra":{"draws":1,"losses":39,"wins":0},"gpt-6-luna":{"draws":12,"losses":8,"wins":8},"gpt-6-sol":{"draws":2,"losses":16,"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":47,"losses":16,"wins":29},"meituan/longcat-2.0":{"draws":30,"losses":45,"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":10,"losses":27,"wins":7},"minimax/minimax-m3":{"draws":32,"losses":29,"wins":41},"mistralai/mistral-medium-3-5":{"draws":5,"losses":7,"wins":6},"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":26,"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":5},"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":39},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":24,"wins":9},"qwen/qwen3.8-27b":{"draws":2,"losses":21,"wins":5},"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":19,"losses":72,"wins":19},"stepfun/step-3.7-flash":{"draws":26,"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":13,"wins":12},"x-ai/grok-4.5":{"draws":12,"losses":45,"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":16,"wins":35},"xiaomi/mimo-v2.5":{"draws":71,"losses":106,"wins":121},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":47,"wins":32},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":9,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":12,"wins":0},"z-ai/glm-5.2":{"draws":55,"losses":67,"wins":60},"z-ai/glm-5.3":{"draws":7,"losses":29,"wins":12},"z-ai/glm-5.3-flash":{"draws":3,"losses":16,"wins":3},"z-ai/glm-5.3-flashx":{"draws":8,"losses":16,"wins":8}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":22,"losses":10,"wins":14},"claude-fable-5":{"draws":6,"losses":17,"wins":11},"claude-fable-5-1":{"draws":4,"losses":33,"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":168,"wins":77},"claude-opus-5-5":{"draws":0,"losses":14,"wins":4},"claude-sonnet-5":{"draws":11,"losses":3,"wins":18},"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":21},"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":17,"losses":12,"wins":19},"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":9,"wins":15},"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":15},"gpt-5.4-mini":{"draws":49,"losses":8,"wins":35},"gpt-5.4-nano":{"draws":47,"losses":44,"wins":73},"gpt-5.5":{"draws":44,"losses":32,"wins":32},"gpt-5.6-luna":{"draws":11,"losses":9,"wins":26},"gpt-5.6-sol":{"draws":15,"losses":6,"wins":13},"gpt-5.6-terra":{"draws":11,"losses":4,"wins":3},"gpt-6-astra":{"draws":2,"losses":22,"wins":0},"gpt-6-luna":{"draws":9,"losses":5,"wins":8},"gpt-6-sol":{"draws":3,"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":18},"meta/muse-spark-1.2":{"draws":9,"losses":13,"wins":8},"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":22,"wins":10},"nex-agi/nex-n2-pro":{"draws":17,"losses":7,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":54,"losses":7,"wins":59},"o3":{"draws":26,"losses":15,"wins":51},"openai/gpt-oss-120b":{"draws":15,"losses":3,"wins":12},"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":35,"losses":10,"wins":31},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":0,"wins":13},"qwen/qwen3.8-27b":{"draws":3,"losses":6,"wins":13},"qwen/qwen3.8-flash":{"draws":11,"losses":5,"wins":14},"qwen/qwen3.8-max":{"draws":11,"losses":15,"wins":16},"qwen/qwen3.8-max-0902":{"draws":13,"losses":9,"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":55},"thinkingmachines/inkling-small":{"draws":7,"losses":4,"wins":21},"x-ai/grok-4.5":{"draws":31,"losses":41,"wins":26},"x-ai/grok-4.6":{"draws":13,"losses":10,"wins":7},"x-ai/grok-4.7":{"draws":1,"losses":13,"wins":12},"x-ai/grok-build-0.1":{"draws":32,"losses":7,"wins":9},"xiaomi/mimo-v2.5":{"draws":92,"losses":22,"wins":80},"xiaomi/mimo-v2.5-pro":{"draws":17,"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":70,"losses":35,"wins":75},"z-ai/glm-5.3":{"draws":8,"losses":16,"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":31,"losses":51,"wins":20},"claude-fable-5-1":{"draws":8,"losses":80,"wins":4},"claude-opus-4-5":{"draws":83,"losses":88,"wins":55},"claude-opus-4-8":{"draws":9,"losses":17,"wins":4},"claude-opus-5":{"draws":8,"losses":56,"wins":10},"claude-opus-5-5":{"draws":1,"losses":9,"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":48,"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":48,"wins":31},"google/gemini-3.5-flash-lite":{"draws":169,"losses":159,"wins":200},"google/gemini-3.6-flash":{"draws":134,"losses":211,"wins":107},"google/gemini-3.8-flash":{"draws":33,"losses":65,"wins":30},"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":17,"wins":6},"gpt-5.4":{"draws":102,"losses":144,"wins":43},"gpt-5.4-mini":{"draws":4,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":14,"losses":19,"wins":15},"gpt-5.5":{"draws":11,"losses":26,"wins":9},"gpt-5.6-luna":{"draws":104,"losses":53,"wins":53},"gpt-5.6-sol":{"draws":42,"losses":177,"wins":47},"gpt-5.6-terra":{"draws":47,"losses":45,"wins":54},"gpt-6-astra":{"draws":16,"losses":80,"wins":0},"gpt-6-luna":{"draws":8,"losses":14,"wins":4},"gpt-6-sol":{"draws":5,"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":50,"losses":50,"wins":66},"meta/muse-glimmer-30b":{"draws":62,"losses":39,"wins":41},"meta/muse-spark-1.2":{"draws":50,"losses":98,"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":84,"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":127,"wins":115},"openai/gpt-oss-120b":{"draws":64,"losses":29,"wins":43},"poolside/laguna-s-2.1":{"draws":72,"losses":40,"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":45,"wins":28},"qwen/qwen3.8-27b":{"draws":17,"losses":35,"wins":20},"qwen/qwen3.8-flash":{"draws":37,"losses":32,"wins":27},"qwen/qwen3.8-max":{"draws":55,"losses":60,"wins":27},"qwen/qwen3.8-max-0902":{"draws":12,"losses":14,"wins":2},"stealth/ox-alpha":{"draws":143,"losses":161,"wins":99},"stepfun/step-3.7-flash":{"draws":20,"losses":26,"wins":20},"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":89},"thinkingmachines/inkling-small":{"draws":68,"losses":52,"wins":50},"x-ai/grok-4.5":{"draws":47,"losses":83,"wins":68},"x-ai/grok-4.6":{"draws":39,"losses":65,"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":16},"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":2,"losses":8,"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":68},"claude-fable-5-1":{"draws":17,"losses":140,"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":78,"wins":15},"claude-opus-5-5":{"draws":1,"losses":17,"wins":2},"claude-sonnet-5":{"draws":48,"losses":43,"wins":232},"cohere/north-mini-code":{"draws":3,"losses":2,"wins":13},"deepseek/deepseek-v4-flash":{"draws":21,"losses":19,"wins":96},"deepseek/deepseek-v4-pro":{"draws":13,"losses":34,"wins":67},"deepseek/deepseek-v4-pro-0813":{"draws":22,"losses":28,"wins":74},"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":43,"wins":90},"google/gemini-3.5-flash-lite":{"draws":70,"losses":41,"wins":355},"google/gemini-3.6-flash":{"draws":60,"losses":133,"wins":237},"google/gemini-3.8-flash":{"draws":20,"losses":59,"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":17},"gpt-5.4":{"draws":59,"losses":95,"wins":136},"gpt-5.4-mini":{"draws":10,"losses":3,"wins":19},"gpt-5.4-nano":{"draws":5,"losses":3,"wins":30},"gpt-5.5":{"draws":15,"losses":13,"wins":6},"gpt-5.6-luna":{"draws":42,"losses":47,"wins":177},"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":141,"wins":16},"gpt-6-luna":{"draws":3,"losses":5,"wins":16},"gpt-6-sol":{"draws":2,"losses":11,"wins":13},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":18,"losses":1,"wins":43},"inclusionai/ling-3.0-flash":{"draws":12,"losses":6,"wins":56},"meituan/longcat-2.0":{"draws":21,"losses":15,"wins":120},"meta/muse-glimmer-30b":{"draws":13,"losses":7,"wins":46},"meta/muse-spark-1.2":{"draws":20,"losses":42,"wins":144},"meta/muse-spark-1.3":{"draws":29,"losses":44,"wins":63},"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":11,"losses":54,"wins":211},"openai/gpt-oss-120b":{"draws":13,"losses":8,"wins":65},"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":51},"qwen/qwen3.8-max":{"draws":33,"losses":32,"wins":78},"qwen/qwen3.8-max-0902":{"draws":5,"losses":2,"wins":11},"stealth/ox-alpha":{"draws":72,"losses":140,"wins":279},"stepfun/step-3.7-flash":{"draws":2,"losses":12,"wins":38},"tencent/hy3-preview":{"draws":5,"losses":3,"wins":12},"tencent/hy4-preview":{"draws":23,"losses":46,"wins":73},"thinkingmachines/inkling":{"draws":27,"losses":12,"wins":125},"thinkingmachines/inkling-small":{"draws":16,"losses":18,"wins":75},"x-ai/grok-4.5":{"draws":27,"losses":78,"wins":121},"x-ai/grok-4.6":{"draws":31,"losses":67,"wins":68},"x-ai/grok-4.7":{"draws":2,"losses":4,"wins":10},"x-ai/grok-build-0.1":{"draws":3,"losses":3,"wins":6},"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":115},"z-ai/glm-5.3":{"draws":26,"losses":66,"wins":68},"z-ai/glm-5.3-flash":{"draws":30,"losses":57,"wins":73},"z-ai/glm-5.3-flashx":{"draws":7,"losses":5,"wins":6}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":24,"wins":56},"claude-fable-5":{"draws":38,"losses":82,"wins":22},"claude-fable-5-1":{"draws":13,"losses":124,"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":49,"wins":2},"claude-opus-5-5":{"draws":2,"losses":20,"wins":0},"claude-sonnet-5":{"draws":49,"losses":38,"wins":53},"cohere/north-mini-code":{"draws":4,"losses":4,"wins":26},"deepseek/deepseek-v4-flash":{"draws":60,"losses":31,"wins":63},"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":7,"wins":2},"google/gemini-3.1-flash-lite":{"draws":9,"losses":6,"wins":33},"google/gemini-3.5-flash":{"draws":47,"losses":40,"wins":51},"google/gemini-3.5-flash-lite":{"draws":74,"losses":52,"wins":108},"google/gemini-3.6-flash":{"draws":66,"losses":88,"wins":60},"google/gemini-3.8-flash":{"draws":47,"losses":54,"wins":33},"google/gemma-4-31b-it":{"draws":3,"losses":1,"wins":14},"gpt-4.1":{"draws":8,"losses":3,"wins":3},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":7},"gpt-5":{"draws":6,"losses":7,"wins":9},"gpt-5.4":{"draws":44,"losses":60,"wins":22},"gpt-5.4-mini":{"draws":12,"losses":4,"wins":14},"gpt-5.4-nano":{"draws":9,"losses":14,"wins":17},"gpt-5.5":{"draws":11,"losses":3,"wins":4},"gpt-5.6-luna":{"draws":47,"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":7,"wins":3},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":8},"inception/mercury-2.5-preview":{"draws":44,"losses":10,"wins":46},"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":47},"meta/muse-spark-1.2":{"draws":34,"losses":44,"wins":30},"meta/muse-spark-1.3":{"draws":30,"losses":67,"wins":37},"minimax/minimax-m3":{"draws":8,"losses":6,"wins":10},"mistralai/mistral-medium-3-5":{"draws":26,"losses":9,"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":41,"losses":11,"wins":38},"qwen/qwen3.7-max":{"draws":10,"losses":8,"wins":20},"qwen/qwen3.7-plus":{"draws":6,"losses":3,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":54,"losses":57,"wins":29},"qwen/qwen3.8-27b":{"draws":22,"losses":28,"wins":28},"qwen/qwen3.8-flash":{"draws":25,"losses":30,"wins":29},"qwen/qwen3.8-max":{"draws":63,"losses":43,"wins":34},"qwen/qwen3.8-max-0902":{"draws":11,"losses":10,"wins":1},"stealth/ox-alpha":{"draws":145,"losses":161,"wins":120},"stepfun/step-3.7-flash":{"draws":11,"losses":7,"wins":18},"tencent/hy3-preview":{"draws":9,"losses":3,"wins":10},"tencent/hy4-preview":{"draws":36,"losses":50,"wins":36},"thinkingmachines/inkling":{"draws":30,"losses":17,"wins":51},"thinkingmachines/inkling-small":{"draws":49,"losses":26,"wins":67},"x-ai/grok-4.5":{"draws":32,"losses":70,"wins":26},"x-ai/grok-4.6":{"draws":48,"losses":79,"wins":25},"x-ai/grok-4.7":{"draws":3,"losses":10,"wins":3},"x-ai/grok-build-0.1":{"draws":6,"losses":4,"wins":8},"xiaomi/mimo-v2.5":{"draws":19,"losses":5,"wins":38},"xiaomi/mimo-v2.5-pro":{"draws":6,"losses":4,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":6,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":5},"z-ai/glm-5.2":{"draws":86,"losses":40,"wins":68},"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":57},"claude-fable-5":{"draws":12,"losses":33,"wins":119},"claude-fable-5-1":{"draws":18,"losses":65,"wins":109},"claude-opus-4-5":{"draws":14,"losses":6,"wins":128},"claude-opus-4-8":{"draws":6,"losses":1,"wins":41},"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":12},"deepseek/deepseek-v4-flash":{"draws":5,"losses":3,"wins":104},"deepseek/deepseek-v4-pro":{"draws":4,"losses":12,"wins":86},"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":152},"google/gemini-3.6-flash":{"draws":20,"losses":14,"wins":162},"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":10},"gpt-5":{"draws":0,"losses":0,"wins":20},"gpt-5.4":{"draws":14,"losses":19,"wins":107},"gpt-5.4-mini":{"draws":1,"losses":0,"wins":13},"gpt-5.4-nano":{"draws":1,"losses":0,"wins":39},"gpt-5.5":{"draws":2,"losses":0,"wins":22},"gpt-5.6-luna":{"draws":16,"losses":0,"wins":80},"gpt-5.6-sol":{"draws":15,"losses":16,"wins":141},"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":14},"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":53},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":63},"meta/muse-spark-1.2":{"draws":11,"losses":2,"wins":83},"meta/muse-spark-1.3":{"draws":15,"losses":12,"wins":101},"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":19},"o3":{"draws":1,"losses":1,"wins":120},"openai/gpt-oss-120b":{"draws":3,"losses":0,"wins":49},"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":17,"losses":3,"wins":106},"qwen/qwen3.8-max-0902":{"draws":3,"losses":2,"wins":21},"stealth/ox-alpha":{"draws":67,"losses":32,"wins":387},"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":68},"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":9},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":11},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":26},"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":117},"z-ai/glm-5.3":{"draws":23,"losses":13,"wins":116},"z-ai/glm-5.3-flash":{"draws":24,"losses":9,"wins":117},"z-ai/glm-5.3-flashx":{"draws":2,"losses":2,"wins":20}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":8,"wins":5},"claude-fable-5":{"draws":5,"losses":11,"wins":2},"claude-fable-5-1":{"draws":1,"losses":15,"wins":0},"claude-opus-4-5":{"draws":18,"losses":16,"wins":10},"claude-opus-4-8":{"draws":2,"losses":5,"wins":3},"claude-opus-5":{"draws":4,"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":0,"wins":3},"deepseek/deepseek-v4-flash":{"draws":6,"losses":6,"wins":10},"deepseek/deepseek-v4-pro":{"draws":4,"losses":2,"wins":16},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":6,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":12,"wins":8},"google/gemini-3.1-flash-lite":{"draws":5,"losses":3,"wins":12},"google/gemini-3.5-flash":{"draws":7,"losses":17,"wins":12},"google/gemini-3.5-flash-lite":{"draws":10,"losses":8,"wins":24},"google/gemini-3.6-flash":{"draws":13,"losses":30,"wins":7},"google/gemini-3.8-flash":{"draws":6,"losses":8,"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":8,"losses":11,"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":9,"losses":8,"wins":5},"gpt-5.6-luna":{"draws":8,"losses":4,"wins":14},"gpt-5.6-sol":{"draws":3,"losses":16,"wins":5},"gpt-5.6-terra":{"draws":2,"losses":9,"wins":5},"gpt-6-astra":{"draws":6,"losses":14,"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":7,"losses":4,"wins":13},"inclusionai/ling-3.0-flash":{"draws":8,"losses":2,"wins":10},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":13},"meta/muse-glimmer-30b":{"draws":7,"losses":3,"wins":8},"meta/muse-spark-1.2":{"draws":2,"losses":7,"wins":3},"meta/muse-spark-1.3":{"draws":5,"losses":11,"wins":4},"minimax/minimax-m3":{"draws":6,"losses":0,"wins":6},"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":7},"o3":{"draws":8,"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":11,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"wins":4},"qwen/qwen3.8-flash":{"draws":0,"losses":5,"wins":3},"qwen/qwen3.8-max":{"draws":9,"losses":13,"wins":4},"qwen/qwen3.8-max-0902":{"draws":21,"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":9,"losses":4,"wins":9},"tencent/hy4-preview":{"draws":2,"losses":7,"wins":5},"thinkingmachines/inkling":{"draws":11,"losses":1,"wins":8},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":10},"x-ai/grok-4.5":{"draws":5,"losses":9,"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":7,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":17,"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":19,"wins":13},"z-ai/glm-5.3":{"draws":3,"losses":11,"wins":2},"z-ai/glm-5.3-flash":{"draws":4,"losses":13,"wins":3},"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":18,"wins":15},"claude-opus-5-5":{"draws":13,"losses":104,"wins":39},"claude-sonnet-5":{"draws":2,"losses":4,"wins":28},"cohere/north-mini-code":{"draws":3,"losses":1,"wins":6},"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":2,"losses":4,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":2,"wins":19},"google/gemini-3.1-flash-lite":{"draws":4,"losses":0,"wins":18},"google/gemini-3.5-flash":{"draws":7,"losses":7,"wins":20},"google/gemini-3.5-flash-lite":{"draws":9,"losses":7,"wins":48},"google/gemini-3.6-flash":{"draws":7,"losses":11,"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":5,"wins":16},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":16},"gpt-5.5":{"draws":3,"losses":2,"wins":21},"gpt-5.6-luna":{"draws":5,"losses":1,"wins":12},"gpt-5.6-sol":{"draws":2,"losses":13,"wins":11},"gpt-5.6-terra":{"draws":2,"losses":3,"wins":7},"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":2,"wins":9},"meituan/longcat-2.0":{"draws":2,"losses":1,"wins":29},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":10},"meta/muse-spark-1.2":{"draws":3,"losses":2,"wins":7},"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":0,"losses":0,"wins":8},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"wins":5},"moonshotai/kimi-k3":{"draws":4,"losses":6,"wins":12},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":4},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":0,"wins":13},"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":15},"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":4,"wins":10},"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":25},"stealth/ox-alpha":{"draws":13,"losses":12,"wins":47},"stepfun/step-3.7-flash":{"draws":1,"losses":1,"wins":14},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":18},"tencent/hy4-preview":{"draws":2,"losses":9,"wins":9},"thinkingmachines/inkling":{"draws":3,"losses":1,"wins":24},"thinkingmachines/inkling-small":{"draws":5,"losses":1,"wins":18},"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":3,"losses":0,"wins":9},"xiaomi/mimo-v2.5":{"draws":6,"losses":1,"wins":27},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":8,"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":12,"wins":10},"z-ai/glm-5.3-flash":{"draws":5,"losses":8,"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":10,"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":11,"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":10,"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":24,"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":4,"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":4,"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":34,"wins":28},"claude-fable-5":{"draws":24,"losses":31,"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":16,"wins":4},"claude-opus-5":{"draws":9,"losses":28,"wins":1},"claude-opus-5-5":{"draws":4,"losses":18,"wins":0},"claude-sonnet-5":{"draws":49,"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":4},"google/gemini-3.5-flash":{"draws":38,"losses":41,"wins":7},"google/gemini-3.5-flash-lite":{"draws":96,"losses":78,"wins":36},"google/gemini-3.6-flash":{"draws":64,"losses":82,"wins":14},"google/gemini-3.8-flash":{"draws":33,"losses":37,"wins":2},"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":43,"wins":1},"gpt-5.6-terra":{"draws":44,"losses":46,"wins":10},"gpt-6-astra":{"draws":7,"losses":35,"wins":0},"gpt-6-luna":{"draws":7,"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":32,"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":29,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":12,"wins":4},"mistralai/mistral-medium-3-5":{"draws":37,"losses":20,"wins":21},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":10,"wins":0},"moonshotai/kimi-k3":{"draws":42,"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":51,"losses":31,"wins":24},"poolside/laguna-s-2.1":{"draws":28,"losses":23,"wins":17},"qwen/qwen3.7-max":{"draws":10,"losses":4,"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":33,"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":97,"losses":134,"wins":38},"stepfun/step-3.7-flash":{"draws":11,"losses":21,"wins":6},"tencent/hy3-preview":{"draws":13,"losses":4,"wins":7},"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":33,"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":7},"xiaomi/mimo-v2.6-flash":{"draws":2,"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":32,"wins":4},"z-ai/glm-5.3-flash":{"draws":35,"losses":39,"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":6,"losses":17,"wins":1},"claude-fable-5-1":{"draws":0,"losses":36,"wins":0},"claude-opus-4-5":{"draws":49,"losses":57,"wins":22},"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":64,"wins":12},"cohere/north-mini-code":{"draws":29,"losses":9,"wins":20},"deepseek/deepseek-v4-flash":{"draws":49,"losses":39,"wins":32},"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":11,"losses":17,"wins":2},"google/gemini-3.1-flash-lite":{"draws":19,"losses":26,"wins":17},"google/gemini-3.5-flash":{"draws":25,"losses":30,"wins":5},"google/gemini-3.5-flash-lite":{"draws":92,"losses":123,"wins":47},"google/gemini-3.6-flash":{"draws":116,"losses":109,"wins":39},"google/gemini-3.8-flash":{"draws":11,"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":20},"gpt-5.4":{"draws":16,"losses":41,"wins":13},"gpt-5.4-mini":{"draws":32,"losses":20,"wins":8},"gpt-5.4-nano":{"draws":47,"losses":29,"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":9,"wins":2},"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":9,"wins":3},"moonshotai/kimi-k3":{"draws":43,"losses":65,"wins":20},"nex-agi/nex-n2-pro":{"draws":32,"losses":21,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":23,"wins":19},"o3":{"draws":23,"losses":89,"wins":36},"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":21,"wins":5},"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":10,"losses":19,"wins":1},"stealth/ox-alpha":{"draws":36,"losses":70,"wins":24},"stepfun/step-3.7-flash":{"draws":18,"losses":26,"wins":10},"tencent/hy3-preview":{"draws":15,"losses":22,"wins":5},"tencent/hy4-preview":{"draws":10,"losses":26,"wins":6},"thinkingmachines/inkling":{"draws":61,"losses":50,"wins":47},"thinkingmachines/inkling-small":{"draws":23,"losses":29,"wins":13},"x-ai/grok-4.5":{"draws":40,"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":56,"losses":44,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":21,"losses":26,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":6,"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":5,"losses":17,"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":20},"claude-fable-5-1":{"draws":1,"losses":48,"wins":3},"claude-opus-4-5":{"draws":68,"losses":130,"wins":47},"claude-opus-4-8":{"draws":15,"losses":40,"wins":19},"claude-opus-5":{"draws":20,"losses":148,"wins":20},"claude-opus-5-5":{"draws":0,"losses":19,"wins":1},"claude-sonnet-5":{"draws":53,"losses":87,"wins":16},"cohere/north-mini-code":{"draws":35,"losses":8,"wins":33},"deepseek/deepseek-v4-flash":{"draws":53,"losses":50,"wins":31},"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":71,"wins":21},"google/gemini-3.5-flash-lite":{"draws":111,"losses":176,"wins":153},"google/gemini-3.6-flash":{"draws":115,"losses":203,"wins":71},"google/gemini-3.8-flash":{"draws":19,"losses":36,"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":44,"wins":22},"gpt-5.4":{"draws":52,"losses":74,"wins":23},"gpt-5.4-mini":{"draws":39,"losses":40,"wins":29},"gpt-5.4-nano":{"draws":30,"losses":69,"wins":45},"gpt-5.5":{"draws":52,"losses":35,"wins":24},"gpt-5.6-luna":{"draws":50,"losses":66,"wins":50},"gpt-5.6-sol":{"draws":21,"losses":120,"wins":15},"gpt-5.6-terra":{"draws":30,"losses":43,"wins":23},"gpt-6-astra":{"draws":5,"losses":53,"wins":2},"gpt-6-luna":{"draws":6,"losses":13,"wins":1},"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":30,"wins":26},"meta/muse-spark-1.2":{"draws":36,"losses":49,"wins":39},"meta/muse-spark-1.3":{"draws":23,"losses":50,"wins":11},"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":34,"losses":29,"wins":35},"poolside/laguna-s-2.1":{"draws":92,"losses":66,"wins":74},"qwen/qwen3.7-max":{"draws":27,"losses":32,"wins":6},"qwen/qwen3.7-plus":{"draws":17,"losses":17,"wins":18},"qwen/qwen3.8-2.4t-a95b":{"draws":17,"losses":50,"wins":13},"qwen/qwen3.8-27b":{"draws":15,"losses":32,"wins":13},"qwen/qwen3.8-flash":{"draws":28,"losses":24,"wins":10},"qwen/qwen3.8-max":{"draws":36,"losses":42,"wins":18},"qwen/qwen3.8-max-0902":{"draws":12,"losses":28,"wins":7},"stealth/ox-alpha":{"draws":67,"losses":169,"wins":44},"stepfun/step-3.7-flash":{"draws":23,"losses":47,"wins":40},"tencent/hy3-preview":{"draws":28,"losses":22,"wins":22},"tencent/hy4-preview":{"draws":22,"losses":47,"wins":13},"thinkingmachines/inkling":{"draws":54,"losses":90,"wins":68},"thinkingmachines/inkling-small":{"draws":29,"losses":32,"wins":38},"x-ai/grok-4.5":{"draws":51,"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":71,"losses":63,"wins":72},"xiaomi/mimo-v2.5-pro":{"draws":30,"losses":34,"wins":24},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":1,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":62,"losses":82,"wins":60},"z-ai/glm-5.3":{"draws":24,"losses":50,"wins":6},"z-ai/glm-5.3-flash":{"draws":23,"losses":43,"wins":22},"z-ai/glm-5.3-flashx":{"draws":15,"losses":11,"wins":5}},"meta/muse-glimmer-30b":{"bytedance-seed/seed-2.0-code":{"draws":59,"losses":45,"wins":34},"claude-fable-5":{"draws":25,"losses":37,"wins":8},"claude-fable-5-1":{"draws":6,"losses":58,"wins":0},"claude-opus-4-5":{"draws":41,"losses":56,"wins":13},"claude-opus-4-8":{"draws":8,"losses":15,"wins":5},"claude-opus-5":{"draws":5,"losses":35,"wins":6},"claude-opus-5-5":{"draws":2,"losses":26,"wins":0},"claude-sonnet-5":{"draws":49,"losses":57,"wins":16},"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":52,"losses":53,"wins":19},"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":88,"losses":94,"wins":30},"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":34,"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":18,"wins":2},"gpt-5.6-luna":{"draws":62,"losses":41,"wins":39},"gpt-5.6-sol":{"draws":13,"losses":46,"wins":7},"gpt-5.6-terra":{"draws":57,"losses":47,"wins":18},"gpt-6-astra":{"draws":5,"losses":63,"wins":0},"gpt-6-luna":{"draws":7,"losses":8,"wins":3},"gpt-6-sol":{"draws":2,"losses":10,"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":30},"meta/muse-glimmer-30b":{"draws":40,"losses":20,"wins":20},"meta/muse-spark-1.2":{"draws":21,"losses":37,"wins":20},"meta/muse-spark-1.3":{"draws":36,"losses":26,"wins":10},"minimax/minimax-m3":{"draws":7,"losses":9,"wins":6},"mistralai/mistral-medium-3-5":{"draws":46,"losses":11,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":0,"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":7,"losses":9,"wins":6},"qwen/qwen3.7-plus":{"draws":11,"losses":7,"wins":8},"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":14,"losses":12,"wins":0},"stealth/ox-alpha":{"draws":119,"losses":196,"wins":57},"stepfun/step-3.7-flash":{"draws":14,"losses":5,"wins":17},"tencent/hy3-preview":{"draws":7,"losses":10,"wins":3},"tencent/hy4-preview":{"draws":42,"losses":49,"wins":13},"thinkingmachines/inkling":{"draws":44,"losses":28,"wins":34},"thinkingmachines/inkling-small":{"draws":72,"losses":26,"wins":54},"x-ai/grok-4.5":{"draws":27,"losses":45,"wins":12},"x-ai/grok-4.6":{"draws":42,"losses":38,"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":30,"losses":13,"wins":19},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":8},"xiaomi/mimo-v2.6-flash":{"draws":3,"losses":6,"wins":3},"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":46,"wins":22},"claude-fable-5-1":{"draws":10,"losses":93,"wins":9},"claude-opus-4-5":{"draws":45,"losses":48,"wins":71},"claude-opus-4-8":{"draws":13,"losses":22,"wins":11},"claude-opus-5":{"draws":4,"losses":40,"wins":10},"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":43},"deepseek/deepseek-v4-pro":{"draws":14,"losses":39,"wins":41},"deepseek/deepseek-v4-pro-0813":{"draws":31,"losses":32,"wins":35},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":6,"wins":6},"google/gemini-3.1-flash-lite":{"draws":9,"losses":1,"wins":12},"google/gemini-3.5-flash":{"draws":25,"losses":49,"wins":36},"google/gemini-3.5-flash-lite":{"draws":89,"losses":72,"wins":177},"google/gemini-3.6-flash":{"draws":64,"losses":130,"wins":152},"google/gemini-3.8-flash":{"draws":19,"losses":40,"wins":43},"google/gemma-4-31b-it":{"draws":11,"losses":1,"wins":12},"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":9},"gpt-5.4-nano":{"draws":2,"losses":7,"wins":9},"gpt-5.5":{"draws":9,"losses":8,"wins":13},"gpt-5.6-luna":{"draws":50,"losses":52,"wins":98},"gpt-5.6-sol":{"draws":20,"losses":144,"wins":42},"gpt-5.6-terra":{"draws":34,"losses":30,"wins":44},"gpt-6-astra":{"draws":11,"losses":83,"wins":2},"gpt-6-luna":{"draws":2,"losses":3,"wins":7},"gpt-6-sol":{"draws":3,"losses":7,"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":37},"meta/muse-spark-1.2":{"draws":22,"losses":39,"wins":39},"meta/muse-spark-1.3":{"draws":23,"losses":36,"wins":27},"minimax/minimax-m3":{"draws":5,"losses":1,"wins":10},"mistralai/mistral-medium-3-5":{"draws":21,"losses":8,"wins":33},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":5,"wins":4},"moonshotai/kimi-k3":{"draws":39,"losses":77,"wins":62},"nex-agi/nex-n2-pro":{"draws":5,"losses":6,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":14},"o3":{"draws":12,"losses":99,"wins":91},"openai/gpt-oss-120b":{"draws":25,"losses":9,"wins":44},"poolside/laguna-s-2.1":{"draws":36,"losses":19,"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":45,"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":27,"losses":36,"wins":34},"qwen/qwen3.8-max-0902":{"draws":5,"losses":14,"wins":5},"stealth/ox-alpha":{"draws":89,"losses":187,"wins":105},"stepfun/step-3.7-flash":{"draws":2,"losses":11,"wins":33},"tencent/hy3-preview":{"draws":7,"losses":8,"wins":15},"tencent/hy4-preview":{"draws":21,"losses":49,"wins":32},"thinkingmachines/inkling":{"draws":47,"losses":21,"wins":68},"thinkingmachines/inkling-small":{"draws":32,"losses":24,"wins":54},"x-ai/grok-4.5":{"draws":33,"losses":83,"wins":40},"x-ai/grok-4.6":{"draws":23,"losses":60,"wins":21},"x-ai/grok-4.7":{"draws":0,"losses":4,"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":5,"losses":18,"wins":23},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":2,"wins":9},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":6,"wins":1},"z-ai/glm-5.2":{"draws":30,"losses":52,"wins":64},"z-ai/glm-5.3":{"draws":21,"losses":57,"wins":24},"z-ai/glm-5.3-flash":{"draws":16,"losses":45,"wins":37},"z-ai/glm-5.3-flashx":{"draws":3,"losses":7,"wins":10}},"meta/muse-spark-1.3":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":19,"wins":46},"claude-fable-5":{"draws":20,"losses":63,"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":64,"wins":14},"claude-opus-5-5":{"draws":0,"losses":16,"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":75},"deepseek/deepseek-v4-pro":{"draws":22,"losses":37,"wins":49},"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":4,"losses":0,"wins":14},"google/gemini-3.5-flash":{"draws":23,"losses":40,"wins":69},"google/gemini-3.5-flash-lite":{"draws":42,"losses":44,"wins":108},"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":24,"losses":46,"wins":44},"gpt-5.4-mini":{"draws":12,"losses":2,"wins":16},"gpt-5.4-nano":{"draws":10,"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":63,"wins":44},"gpt-5.6-terra":{"draws":30,"losses":37,"wins":67},"gpt-6-astra":{"draws":15,"losses":101,"wins":12},"gpt-6-luna":{"draws":5,"losses":4,"wins":11},"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":29},"inclusionai/ling-3.0-flash":{"draws":8,"losses":7,"wins":27},"meituan/longcat-2.0":{"draws":23,"losses":11,"wins":50},"meta/muse-glimmer-30b":{"draws":36,"losses":10,"wins":26},"meta/muse-spark-1.2":{"draws":23,"losses":27,"wins":36},"meta/muse-spark-1.3":{"draws":12,"losses":24,"wins":24},"minimax/minimax-m3":{"draws":2,"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":9,"losses":5,"wins":22},"o3":{"draws":12,"losses":36,"wins":92},"openai/gpt-oss-120b":{"draws":30,"losses":14,"wins":54},"poolside/laguna-s-2.1":{"draws":24,"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":45,"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":60},"qwen/qwen3.8-max-0902":{"draws":12,"losses":5,"wins":9},"stealth/ox-alpha":{"draws":103,"losses":160,"wins":160},"stepfun/step-3.7-flash":{"draws":8,"losses":8,"wins":34},"tencent/hy3-preview":{"draws":2,"losses":4,"wins":20},"tencent/hy4-preview":{"draws":26,"losses":52,"wins":40},"thinkingmachines/inkling":{"draws":23,"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":2,"losses":14,"wins":4},"x-ai/grok-build-0.1":{"draws":7,"losses":3,"wins":10},"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":6,"losses":5,"wins":11},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":34,"losses":37,"wins":51},"z-ai/glm-5.3":{"draws":28,"losses":73,"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":20,"wins":8},"claude-fable-5":{"draws":5,"losses":15,"wins":2},"claude-fable-5-1":{"draws":1,"losses":16,"wins":1},"claude-opus-4-5":{"draws":28,"losses":59,"wins":13},"claude-opus-4-8":{"draws":22,"losses":42,"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":5,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":13,"wins":3},"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":15,"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":6,"wins":0},"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":4,"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":2,"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":13,"wins":3},"moonshotai/kimi-k3":{"draws":12,"losses":18,"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":33,"wins":10},"openai/gpt-oss-120b":{"draws":8,"losses":14,"wins":4},"poolside/laguna-s-2.1":{"draws":26,"losses":24,"wins":20},"qwen/qwen3.7-max":{"draws":29,"losses":33,"wins":14},"qwen/qwen3.7-plus":{"draws":13,"losses":20,"wins":19},"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":8,"losses":7,"wins":3},"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":4},"x-ai/grok-4.5":{"draws":8,"losses":32,"wins":4},"x-ai/grok-4.6":{"draws":5,"losses":13,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":4,"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":8,"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":36,"losses":23,"wins":19},"claude-fable-5":{"draws":22,"losses":18,"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":23,"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":1,"losses":7,"wins":4},"deepseek/deepseek-v4-flash":{"draws":37,"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":6,"losses":6,"wins":6},"google/gemini-3.5-flash":{"draws":22,"losses":39,"wins":13},"google/gemini-3.5-flash-lite":{"draws":60,"losses":66,"wins":34},"google/gemini-3.6-flash":{"draws":44,"losses":54,"wins":18},"google/gemini-3.8-flash":{"draws":21,"losses":30,"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":7,"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":6,"wins":7},"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":26,"losses":43,"wins":9},"gpt-6-astra":{"draws":1,"losses":37,"wins":0},"gpt-6-luna":{"draws":3,"losses":3,"wins":0},"gpt-6-sol":{"draws":0,"losses":8,"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":46,"losses":33,"wins":11},"meta/muse-spark-1.2":{"draws":21,"losses":33,"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":36,"wins":7},"nex-agi/nex-n2-pro":{"draws":11,"losses":6,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":6,"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":51,"wins":3},"qwen/qwen3.8-27b":{"draws":9,"losses":27,"wins":6},"qwen/qwen3.8-flash":{"draws":24,"losses":24,"wins":8},"qwen/qwen3.8-max":{"draws":29,"losses":39,"wins":10},"qwen/qwen3.8-max-0902":{"draws":6,"losses":10,"wins":0},"stealth/ox-alpha":{"draws":73,"losses":121,"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":8,"losses":6,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":7,"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":50,"losses":53,"wins":19},"z-ai/glm-5.3":{"draws":23,"losses":28,"wins":7},"z-ai/glm-5.3-flash":{"draws":23,"losses":29,"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":10,"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":9,"wins":5},"google/gemini-3.6-flash":{"draws":6,"losses":18,"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":0,"losses":8,"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":2,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":9},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":14},"meta/muse-glimmer-30b":{"draws":0,"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":13},"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":3,"wins":17},"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":3,"losses":5,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":4},"stealth/ox-alpha":{"draws":5,"losses":9,"wins":10},"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":10,"losses":19,"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":28,"losses":21,"wins":45},"claude-fable-5":{"draws":26,"losses":82,"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":16,"wins":27},"claude-opus-5":{"draws":22,"losses":114,"wins":26},"claude-opus-5-5":{"draws":1,"losses":17,"wins":6},"claude-sonnet-5":{"draws":86,"losses":58,"wins":112},"cohere/north-mini-code":{"draws":8,"losses":4,"wins":18},"deepseek/deepseek-v4-flash":{"draws":49,"losses":39,"wins":58},"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":15},"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":155,"losses":214,"wins":175},"google/gemini-3.8-flash":{"draws":47,"losses":60,"wins":31},"google/gemma-4-31b-it":{"draws":9,"losses":5,"wins":32},"gpt-4.1":{"draws":8,"losses":3,"wins":9},"gpt-4.1-nano":{"draws":6,"losses":0,"wins":6},"gpt-5":{"draws":18,"losses":15,"wins":15},"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":10,"wins":22},"gpt-5.6-luna":{"draws":84,"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":12,"wins":6},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":42,"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":39,"losses":62,"wins":77},"meta/muse-spark-1.3":{"draws":34,"losses":62,"wins":46},"minimax/minimax-m3":{"draws":12,"losses":4,"wins":18},"mistralai/mistral-medium-3-5":{"draws":25,"losses":7,"wins":36},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":7,"wins":3},"moonshotai/kimi-k3":{"draws":80,"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":38,"losses":133,"wins":137},"openai/gpt-oss-120b":{"draws":39,"losses":15,"wins":60},"poolside/laguna-s-2.1":{"draws":89,"losses":23,"wins":94},"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":46,"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":12,"wins":4},"stealth/ox-alpha":{"draws":113,"losses":173,"wins":135},"stepfun/step-3.7-flash":{"draws":20,"losses":11,"wins":47},"tencent/hy3-preview":{"draws":15,"losses":3,"wins":12},"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":85,"losses":107,"wins":82},"x-ai/grok-4.6":{"draws":46,"losses":57,"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":28,"losses":12,"wins":60},"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":67,"losses":34,"wins":51},"z-ai/glm-5.3":{"draws":29,"losses":70,"wins":27},"z-ai/glm-5.3-flash":{"draws":47,"losses":50,"wins":33},"z-ai/glm-5.3-flashx":{"draws":10,"losses":9,"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":16,"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":2},"deepseek/deepseek-v4-pro-0813":{"draws":7,"losses":11,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":6,"wins":2},"google/gemini-3.1-flash-lite":{"draws":14,"losses":19,"wins":27},"google/gemini-3.5-flash":{"draws":9,"losses":13,"wins":8},"google/gemini-3.5-flash-lite":{"draws":25,"losses":9,"wins":8},"google/gemini-3.6-flash":{"draws":17,"losses":39,"wins":12},"google/gemini-3.8-flash":{"draws":2,"losses":11,"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":9,"wins":2},"gpt-5.4-mini":{"draws":27,"losses":20,"wins":13},"gpt-5.4-nano":{"draws":22,"losses":40,"wins":26},"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":32,"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":11,"losses":9,"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":35,"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":15,"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":15,"losses":19,"wins":20},"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":35},"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":44,"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":36,"wins":0},"claude-opus-4-5":{"draws":67,"losses":72,"wins":29},"claude-opus-4-8":{"draws":21,"losses":66,"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":27,"wins":42},"google/gemini-3.5-flash":{"draws":20,"losses":12,"wins":8},"google/gemini-3.5-flash-lite":{"draws":41,"losses":33,"wins":26},"google/gemini-3.6-flash":{"draws":31,"losses":52,"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":4,"losses":15,"wins":1},"gpt-5.4-mini":{"draws":54,"losses":27,"wins":25},"gpt-5.4-nano":{"draws":45,"losses":40,"wins":37},"gpt-5.5":{"draws":54,"losses":59,"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":19,"wins":0},"gpt-6-luna":{"draws":12,"losses":7,"wins":3},"gpt-6-sol":{"draws":5,"losses":13,"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":19,"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":14,"wins":2},"meta/muse-spark-1.3":{"draws":9,"losses":22,"wins":5},"minimax/minimax-m3":{"draws":31,"losses":30,"wins":25},"mistralai/mistral-medium-3-5":{"draws":9,"losses":3,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":20,"losses":17,"wins":3},"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":50,"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":47,"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":4},"qwen/qwen3.8-max-0902":{"draws":9,"losses":16,"wins":1},"stealth/ox-alpha":{"draws":22,"losses":55,"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":16,"losses":17,"wins":3},"thinkingmachines/inkling":{"draws":48,"losses":35,"wins":41},"thinkingmachines/inkling-small":{"draws":15,"losses":9,"wins":10},"x-ai/grok-4.5":{"draws":21,"losses":43,"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":43,"losses":8,"wins":9},"xiaomi/mimo-v2.5":{"draws":110,"losses":57,"wins":69},"xiaomi/mimo-v2.5-pro":{"draws":20,"losses":24,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":11,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":9,"wins":1},"z-ai/glm-5.2":{"draws":90,"losses":51,"wins":29},"z-ai/glm-5.3":{"draws":6,"losses":23,"wins":7},"z-ai/glm-5.3-flash":{"draws":7,"losses":14,"wins":3},"z-ai/glm-5.3-flashx":{"draws":6,"losses":12,"wins":4}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":23,"losses":42,"wins":67},"claude-fable-5":{"draws":9,"losses":101,"wins":20},"claude-fable-5-1":{"draws":0,"losses":116,"wins":6},"claude-opus-4-5":{"draws":58,"losses":220,"wins":106},"claude-opus-4-8":{"draws":9,"losses":72,"wins":25},"claude-opus-5":{"draws":4,"losses":157,"wins":9},"claude-opus-5-5":{"draws":1,"losses":27,"wins":2},"claude-sonnet-5":{"draws":26,"losses":153,"wins":133},"cohere/north-mini-code":{"draws":23,"losses":16,"wins":23},"deepseek/deepseek-v4-flash":{"draws":32,"losses":72,"wins":92},"deepseek/deepseek-v4-pro":{"draws":27,"losses":75,"wins":46},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":66,"wins":39},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":17,"wins":6},"google/gemini-3.1-flash-lite":{"draws":12,"losses":5,"wins":59},"google/gemini-3.5-flash":{"draws":23,"losses":92,"wins":49},"google/gemini-3.5-flash-lite":{"draws":111,"losses":229,"wins":378},"google/gemini-3.6-flash":{"draws":110,"losses":327,"wins":219},"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":52,"wins":32},"gpt-5.4":{"draws":30,"losses":185,"wins":55},"gpt-5.4-mini":{"draws":10,"losses":20,"wins":22},"gpt-5.4-nano":{"draws":8,"losses":57,"wins":55},"gpt-5.5":{"draws":26,"losses":51,"wins":15},"gpt-5.6-luna":{"draws":38,"losses":115,"wins":127},"gpt-5.6-sol":{"draws":11,"losses":211,"wins":54},"gpt-5.6-terra":{"draws":22,"losses":75,"wins":57},"gpt-6-astra":{"draws":1,"losses":120,"wins":1},"gpt-6-luna":{"draws":8,"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":36,"wins":89},"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":92,"wins":36},"minimax/minimax-m3":{"draws":11,"losses":10,"wins":33},"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":38,"losses":137,"wins":133},"nex-agi/nex-n2-pro":{"draws":7,"losses":10,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"losses":21,"wins":55},"o3":{"draws":44,"losses":202,"wins":202},"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":25},"qwen/qwen3.7-plus":{"draws":8,"losses":18,"wins":24},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":76,"wins":46},"qwen/qwen3.8-27b":{"draws":21,"losses":60,"wins":33},"qwen/qwen3.8-flash":{"draws":26,"losses":35,"wins":39},"qwen/qwen3.8-max":{"draws":28,"losses":83,"wins":47},"qwen/qwen3.8-max-0902":{"draws":4,"losses":15,"wins":7},"stealth/ox-alpha":{"draws":51,"losses":208,"wins":179},"stepfun/step-3.7-flash":{"draws":37,"losses":50,"wins":103},"tencent/hy3-preview":{"draws":24,"losses":21,"wins":25},"tencent/hy4-preview":{"draws":19,"losses":73,"wins":52},"thinkingmachines/inkling":{"draws":61,"losses":64,"wins":162},"thinkingmachines/inkling-small":{"draws":54,"losses":49,"wins":70},"x-ai/grok-4.5":{"draws":24,"losses":169,"wins":83},"x-ai/grok-4.6":{"draws":31,"losses":75,"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":77},"xiaomi/mimo-v2.5-pro":{"draws":14,"losses":43,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":18,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":38,"losses":89,"wins":95},"z-ai/glm-5.3":{"draws":9,"losses":104,"wins":27},"z-ai/glm-5.3-flash":{"draws":29,"losses":61,"wins":58},"z-ai/glm-5.3-flashx":{"draws":1,"losses":29,"wins":12}},"openai/gpt-oss-120b":{"bytedance-seed/seed-2.0-code":{"draws":49,"losses":43,"wins":36},"claude-fable-5":{"draws":28,"losses":51,"wins":11},"claude-fable-5-1":{"draws":7,"losses":62,"wins":1},"claude-opus-4-5":{"draws":24,"losses":65,"wins":11},"claude-opus-4-8":{"draws":4,"losses":6,"wins":0},"claude-opus-5":{"draws":8,"losses":52,"wins":0},"claude-opus-5-5":{"draws":1,"losses":31,"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":20},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":18,"wins":7},"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":86,"losses":83,"wins":73},"google/gemini-3.6-flash":{"draws":72,"losses":81,"wins":29},"google/gemini-3.8-flash":{"draws":25,"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":10,"losses":10,"wins":4},"gpt-5.4":{"draws":58,"losses":39,"wins":15},"gpt-5.4-mini":{"draws":6,"losses":6,"wins":6},"gpt-5.4-nano":{"draws":0,"losses":5,"wins":17},"gpt-5.5":{"draws":15,"losses":12,"wins":3},"gpt-5.6-luna":{"draws":64,"losses":43,"wins":29},"gpt-5.6-sol":{"draws":13,"losses":65,"wins":8},"gpt-5.6-terra":{"draws":45,"losses":72,"wins":13},"gpt-6-astra":{"draws":3,"losses":49,"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":10},"inception/mercury-2.5-preview":{"draws":51,"losses":24,"wins":31},"inclusionai/ling-3.0-flash":{"draws":12,"losses":8,"wins":36},"meituan/longcat-2.0":{"draws":34,"losses":35,"wins":29},"meta/muse-glimmer-30b":{"draws":57,"losses":33,"wins":36},"meta/muse-spark-1.2":{"draws":25,"losses":44,"wins":9},"meta/muse-spark-1.3":{"draws":30,"losses":54,"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":60,"wins":15},"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":19,"wins":19},"poolside/laguna-s-2.1":{"draws":39,"losses":25,"wins":20},"qwen/qwen3.7-max":{"draws":9,"losses":6,"wins":7},"qwen/qwen3.7-plus":{"draws":8,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":45,"losses":47,"wins":10},"qwen/qwen3.8-27b":{"draws":14,"losses":39,"wins":17},"qwen/qwen3.8-flash":{"draws":31,"losses":25,"wins":22},"qwen/qwen3.8-max":{"draws":52,"losses":56,"wins":10},"qwen/qwen3.8-max-0902":{"draws":10,"losses":20,"wins":4},"stealth/ox-alpha":{"draws":106,"losses":176,"wins":55},"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":36,"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":2,"losses":3,"wins":1},"xiaomi/mimo-v2.5":{"draws":31,"losses":16,"wins":17},"xiaomi/mimo-v2.5-pro":{"draws":8,"losses":8,"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":70,"losses":60,"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":8,"losses":12,"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":69,"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":179,"wins":16},"claude-opus-5-5":{"draws":0,"losses":26,"wins":0},"claude-sonnet-5":{"draws":55,"losses":86,"wins":11},"cohere/north-mini-code":{"draws":37,"losses":24,"wins":3},"deepseek/deepseek-v4-flash":{"draws":68,"losses":42,"wins":34},"deepseek/deepseek-v4-pro":{"draws":34,"losses":34,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":41,"losses":31,"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":40,"losses":46,"wins":20},"google/gemini-3.5-flash-lite":{"draws":192,"losses":117,"wins":139},"google/gemini-3.6-flash":{"draws":167,"losses":154,"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":10,"losses":14,"wins":10},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":6},"gpt-5":{"draws":26,"losses":24,"wins":30},"gpt-5.4":{"draws":62,"losses":57,"wins":11},"gpt-5.4-mini":{"draws":43,"losses":23,"wins":16},"gpt-5.4-nano":{"draws":48,"losses":34,"wins":48},"gpt-5.5":{"draws":44,"losses":32,"wins":22},"gpt-5.6-luna":{"draws":72,"losses":54,"wins":40},"gpt-5.6-sol":{"draws":33,"losses":134,"wins":3},"gpt-5.6-terra":{"draws":41,"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":15,"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":92,"losses":74,"wins":66},"meta/muse-glimmer-30b":{"draws":50,"losses":19,"wins":25},"meta/muse-spark-1.2":{"draws":36,"losses":65,"wins":19},"meta/muse-spark-1.3":{"draws":24,"losses":37,"wins":15},"minimax/minimax-m3":{"draws":26,"losses":20,"wins":24},"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":89,"losses":94,"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":46,"wins":46},"qwen/qwen3.7-max":{"draws":26,"losses":23,"wins":19},"qwen/qwen3.7-plus":{"draws":32,"losses":6,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":39,"losses":37,"wins":8},"qwen/qwen3.8-27b":{"draws":14,"losses":31,"wins":17},"qwen/qwen3.8-flash":{"draws":32,"losses":22,"wins":12},"qwen/qwen3.8-max":{"draws":39,"losses":23,"wins":19},"qwen/qwen3.8-max-0902":{"draws":5,"losses":3,"wins":4},"stealth/ox-alpha":{"draws":97,"losses":139,"wins":43},"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":36,"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":8,"wins":2},"x-ai/grok-build-0.1":{"draws":23,"losses":17,"wins":10},"xiaomi/mimo-v2.5":{"draws":54,"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":109,"losses":62,"wins":47},"z-ai/glm-5.3":{"draws":27,"losses":44,"wins":5},"z-ai/glm-5.3-flash":{"draws":42,"losses":44,"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":5,"losses":12,"wins":9},"claude-fable-5":{"draws":4,"losses":13,"wins":3},"claude-fable-5-1":{"draws":1,"losses":21,"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":104,"wins":17},"claude-opus-5-5":{"draws":0,"losses":20,"wins":0},"claude-sonnet-5":{"draws":3,"losses":18,"wins":5},"cohere/north-mini-code":{"draws":19,"losses":10,"wins":29},"deepseek/deepseek-v4-flash":{"draws":28,"losses":14,"wins":22},"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":2,"wins":5},"google/gemini-3.1-flash-lite":{"draws":20,"losses":12,"wins":28},"google/gemini-3.5-flash":{"draws":18,"losses":12,"wins":14},"google/gemini-3.5-flash-lite":{"draws":25,"losses":27,"wins":12},"google/gemini-3.6-flash":{"draws":15,"losses":42,"wins":11},"google/gemini-3.8-flash":{"draws":4,"losses":13,"wins":9},"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":25,"wins":14},"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":20,"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":10,"losses":6,"wins":4},"inclusionai/ling-3.0-flash":{"draws":35,"losses":7,"wins":28},"meituan/longcat-2.0":{"draws":27,"losses":6,"wins":32},"meta/muse-glimmer-30b":{"draws":7,"losses":6,"wins":9},"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":15,"losses":6,"wins":27},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":47,"losses":15,"wins":24},"o3":{"draws":18,"losses":25,"wins":15},"openai/gpt-oss-120b":{"draws":9,"losses":7,"wins":6},"poolside/laguna-s-2.1":{"draws":26,"losses":19,"wins":23},"qwen/qwen3.7-max":{"draws":12,"losses":8,"wins":8},"qwen/qwen3.7-plus":{"draws":24,"losses":12,"wins":22},"qwen/qwen3.8-2.4t-a95b":{"draws":8,"losses":8,"wins":4},"qwen/qwen3.8-27b":{"draws":0,"losses":18,"wins":6},"qwen/qwen3.8-flash":{"draws":12,"losses":7,"wins":9},"qwen/qwen3.8-max":{"draws":16,"losses":11,"wins":5},"qwen/qwen3.8-max-0902":{"draws":6,"losses":3,"wins":1},"stealth/ox-alpha":{"draws":14,"losses":42,"wins":20},"stepfun/step-3.7-flash":{"draws":18,"losses":8,"wins":22},"tencent/hy3-preview":{"draws":28,"losses":12,"wins":26},"tencent/hy4-preview":{"draws":7,"losses":11,"wins":4},"thinkingmachines/inkling":{"draws":31,"losses":12,"wins":35},"thinkingmachines/inkling-small":{"draws":5,"losses":10,"wins":11},"x-ai/grok-4.5":{"draws":18,"losses":22,"wins":14},"x-ai/grok-4.6":{"draws":3,"losses":7,"wins":2},"x-ai/grok-4.7":{"draws":1,"losses":9,"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":3,"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":5,"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":10,"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":17,"losses":18,"wins":31},"google/gemini-3.5-flash":{"draws":13,"losses":12,"wins":3},"google/gemini-3.5-flash-lite":{"draws":23,"losses":17,"wins":12},"google/gemini-3.6-flash":{"draws":21,"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":17,"wins":4},"gpt-5.4-mini":{"draws":20,"losses":16,"wins":24},"gpt-5.4-nano":{"draws":22,"losses":39,"wins":43},"gpt-5.5":{"draws":35,"losses":31,"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":18,"wins":17},"meta/muse-glimmer-30b":{"draws":11,"losses":8,"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":19,"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":8,"losses":3,"wins":1},"poolside/laguna-s-2.1":{"draws":32,"losses":22,"wins":6},"qwen/qwen3.7-max":{"draws":24,"losses":22,"wins":12},"qwen/qwen3.7-plus":{"draws":4,"losses":6,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":11,"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":3,"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":5,"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":13,"losses":25,"wins":8},"x-ai/grok-4.6":{"draws":7,"losses":5,"wins":2},"x-ai/grok-4.7":{"draws":0,"losses":14,"wins":0},"x-ai/grok-build-0.1":{"draws":12,"losses":6,"wins":14},"xiaomi/mimo-v2.5":{"draws":57,"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":9,"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":61,"wins":39},"claude-fable-5-1":{"draws":17,"losses":133,"wins":8},"claude-opus-4-5":{"draws":53,"losses":41,"wins":50},"claude-opus-4-8":{"draws":22,"losses":13,"wins":11},"claude-opus-5":{"draws":14,"losses":53,"wins":15},"claude-opus-5-5":{"draws":2,"losses":14,"wins":4},"claude-sonnet-5":{"draws":59,"losses":36,"wins":51},"cohere/north-mini-code":{"draws":0,"losses":2,"wins":24},"deepseek/deepseek-v4-flash":{"draws":53,"losses":31,"wins":72},"deepseek/deepseek-v4-pro":{"draws":43,"losses":35,"wins":54},"deepseek/deepseek-v4-pro-0813":{"draws":40,"losses":46,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":15,"wins":16},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":39,"losses":50,"wins":55},"google/gemini-3.5-flash-lite":{"draws":77,"losses":40,"wins":111},"google/gemini-3.6-flash":{"draws":64,"losses":100,"wins":76},"google/gemini-3.8-flash":{"draws":32,"losses":66,"wins":50},"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":10,"wins":14},"gpt-5.4":{"draws":32,"losses":50,"wins":60},"gpt-5.4-mini":{"draws":9,"losses":1,"wins":10},"gpt-5.4-nano":{"draws":13,"losses":9,"wins":24},"gpt-5.5":{"draws":9,"losses":13,"wins":0},"gpt-5.6-luna":{"draws":57,"losses":28,"wins":45},"gpt-5.6-sol":{"draws":35,"losses":86,"wins":43},"gpt-5.6-terra":{"draws":54,"losses":29,"wins":57},"gpt-6-astra":{"draws":10,"losses":113,"wins":7},"gpt-6-luna":{"draws":6,"losses":3,"wins":11},"gpt-6-sol":{"draws":0,"losses":10,"wins":4},"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":50},"meta/muse-glimmer-30b":{"draws":49,"losses":17,"wins":40},"meta/muse-spark-1.2":{"draws":28,"losses":29,"wins":45},"meta/muse-spark-1.3":{"draws":41,"losses":50,"wins":45},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":14},"mistralai/mistral-medium-3-5":{"draws":32,"losses":3,"wins":51},"moonshotai/kimi-k2.7-code":{"draws":4,"losses":3,"wins":1},"moonshotai/kimi-k3":{"draws":50,"losses":50,"wins":46},"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":76},"openai/gpt-oss-120b":{"draws":45,"losses":10,"wins":47},"poolside/laguna-s-2.1":{"draws":39,"losses":8,"wins":37},"qwen/qwen3.7-max":{"draws":8,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":11,"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":51},"qwen/qwen3.8-max-0902":{"draws":10,"losses":11,"wins":7},"stealth/ox-alpha":{"draws":135,"losses":169,"wins":158},"stepfun/step-3.7-flash":{"draws":9,"losses":7,"wins":16},"tencent/hy3-preview":{"draws":8,"losses":7,"wins":9},"tencent/hy4-preview":{"draws":42,"losses":56,"wins":42},"thinkingmachines/inkling":{"draws":42,"losses":12,"wins":34},"thinkingmachines/inkling-small":{"draws":46,"losses":17,"wins":79},"x-ai/grok-4.5":{"draws":28,"losses":49,"wins":33},"x-ai/grok-4.6":{"draws":43,"losses":56,"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":17},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":4,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":7,"losses":9,"wins":4},"z-ai/glm-5.2":{"draws":67,"losses":52,"wins":63},"z-ai/glm-5.3":{"draws":37,"losses":76,"wins":29},"z-ai/glm-5.3-flash":{"draws":37,"losses":47,"wins":52},"z-ai/glm-5.3-flashx":{"draws":7,"losses":14,"wins":9}},"qwen/qwen3.8-27b":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":20,"wins":34},"claude-fable-5":{"draws":10,"losses":43,"wins":17},"claude-fable-5-1":{"draws":3,"losses":68,"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":19,"losses":26,"wins":25},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":15},"deepseek/deepseek-v4-flash":{"draws":19,"losses":33,"wins":44},"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":17},"google/gemini-3.5-flash":{"draws":21,"losses":24,"wins":39},"google/gemini-3.5-flash-lite":{"draws":29,"losses":33,"wins":78},"google/gemini-3.6-flash":{"draws":33,"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":36,"wins":15},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":6},"gpt-5.4-nano":{"draws":2,"losses":5,"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":28,"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":5,"wins":21},"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":21,"losses":33,"wins":60},"openai/gpt-oss-120b":{"draws":14,"losses":17,"wins":39},"poolside/laguna-s-2.1":{"draws":14,"losses":17,"wins":31},"qwen/qwen3.7-max":{"draws":0,"losses":6,"wins":18},"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":25},"qwen/qwen3.8-max-0902":{"draws":0,"losses":4,"wins":6},"stealth/ox-alpha":{"draws":61,"losses":112,"wins":92},"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":37},"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":19,"losses":29,"wins":26},"x-ai/grok-4.7":{"draws":0,"losses":8,"wins":2},"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":40,"wins":13},"z-ai/glm-5.3-flash":{"draws":25,"losses":34,"wins":31},"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":29,"losses":42,"wins":13},"claude-fable-5-1":{"draws":5,"losses":77,"wins":4},"claude-opus-4-5":{"draws":30,"losses":31,"wins":31},"claude-opus-4-8":{"draws":9,"losses":11,"wins":8},"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":26,"losses":30,"wins":30},"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":4},"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":64,"losses":59,"wins":39},"google/gemini-3.8-flash":{"draws":24,"losses":47,"wins":21},"google/gemma-4-31b-it":{"draws":10,"losses":3,"wins":7},"gpt-4.1":{"draws":2,"losses":2,"wins":12},"gpt-4.1-nano":{"draws":1,"losses":0,"wins":3},"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":5},"gpt-5.4-nano":{"draws":12,"losses":5,"wins":7},"gpt-5.5":{"draws":11,"losses":14,"wins":5},"gpt-5.6-luna":{"draws":37,"losses":27,"wins":32},"gpt-5.6-sol":{"draws":21,"losses":51,"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":3,"wins":5},"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":33,"losses":7,"wins":32},"inclusionai/ling-3.0-flash":{"draws":18,"losses":9,"wins":27},"meituan/longcat-2.0":{"draws":28,"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":24},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":0,"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":26,"losses":39,"wins":35},"openai/gpt-oss-120b":{"draws":31,"losses":22,"wins":25},"poolside/laguna-s-2.1":{"draws":32,"losses":12,"wins":22},"qwen/qwen3.7-max":{"draws":12,"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":28},"qwen/qwen3.8-max-0902":{"draws":7,"losses":5,"wins":8},"stealth/ox-alpha":{"draws":88,"losses":106,"wins":83},"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":45,"losses":16,"wins":31},"x-ai/grok-4.5":{"draws":14,"losses":31,"wins":13},"x-ai/grok-4.6":{"draws":33,"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":47,"losses":25,"wins":44},"z-ai/glm-5.3":{"draws":24,"losses":55,"wins":13},"z-ai/glm-5.3-flash":{"draws":29,"losses":24,"wins":31},"z-ai/glm-5.3-flashx":{"draws":6,"losses":11,"wins":7}},"qwen/qwen3.8-max":{"bytedance-seed/seed-2.0-code":{"draws":47,"losses":44,"wins":47},"claude-fable-5":{"draws":21,"losses":72,"wins":39},"claude-fable-5-1":{"draws":6,"losses":137,"wins":5},"claude-opus-4-5":{"draws":44,"losses":38,"wins":71},"claude-opus-4-8":{"draws":14,"losses":19,"wins":15},"claude-opus-5":{"draws":11,"losses":50,"wins":9},"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":14},"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":45,"losses":37,"wins":40},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":12,"wins":7},"google/gemini-3.1-flash-lite":{"draws":5,"losses":0,"wins":9},"google/gemini-3.5-flash":{"draws":48,"losses":51,"wins":33},"google/gemini-3.5-flash-lite":{"draws":83,"losses":55,"wins":87},"google/gemini-3.6-flash":{"draws":68,"losses":93,"wins":88},"google/gemini-3.8-flash":{"draws":39,"losses":54,"wins":43},"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":11},"gpt-5.4":{"draws":41,"losses":50,"wins":49},"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":15},"gpt-5.6-luna":{"draws":55,"losses":27,"wins":60},"gpt-5.6-sol":{"draws":33,"losses":78,"wins":32},"gpt-5.6-terra":{"draws":63,"losses":34,"wins":43},"gpt-6-astra":{"draws":17,"losses":106,"wins":3},"gpt-6-luna":{"draws":9,"losses":4,"wins":13},"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":27,"losses":34,"wins":36},"meta/muse-spark-1.3":{"draws":27,"losses":60,"wins":25},"minimax/minimax-m3":{"draws":8,"losses":3,"wins":7},"mistralai/mistral-medium-3-5":{"draws":29,"losses":10,"wins":39},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":2},"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":4,"wins":19},"o3":{"draws":28,"losses":47,"wins":83},"openai/gpt-oss-120b":{"draws":52,"losses":10,"wins":56},"poolside/laguna-s-2.1":{"draws":39,"losses":19,"wins":23},"qwen/qwen3.7-max":{"draws":16,"losses":5,"wins":11},"qwen/qwen3.7-plus":{"draws":3,"losses":10,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":54,"losses":51,"wins":43},"qwen/qwen3.8-27b":{"draws":20,"losses":25,"wins":29},"qwen/qwen3.8-flash":{"draws":35,"losses":28,"wins":23},"qwen/qwen3.8-max":{"draws":54,"losses":57,"wins":57},"qwen/qwen3.8-max-0902":{"draws":5,"losses":12,"wins":5},"stealth/ox-alpha":{"draws":129,"losses":183,"wins":158},"stepfun/step-3.7-flash":{"draws":6,"losses":3,"wins":23},"tencent/hy3-preview":{"draws":6,"losses":5,"wins":7},"tencent/hy4-preview":{"draws":31,"losses":62,"wins":45},"thinkingmachines/inkling":{"draws":38,"losses":21,"wins":41},"thinkingmachines/inkling-small":{"draws":98,"losses":68,"wins":111},"x-ai/grok-4.5":{"draws":33,"losses":43,"wins":37},"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":1},"xiaomi/mimo-v2.5":{"draws":35,"losses":7,"wins":28},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":7,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":14,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":4,"wins":9},"z-ai/glm-5.2":{"draws":64,"losses":43,"wins":53},"z-ai/glm-5.3":{"draws":31,"losses":66,"wins":27},"z-ai/glm-5.3-flash":{"draws":42,"losses":45,"wins":53},"z-ai/glm-5.3-flashx":{"draws":14,"losses":4,"wins":6}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":7,"losses":2,"wins":9},"claude-fable-5":{"draws":8,"losses":14,"wins":4},"claude-fable-5-1":{"draws":2,"losses":23,"wins":5},"claude-opus-4-5":{"draws":7,"losses":7,"wins":14},"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":27,"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":26},"deepseek/deepseek-v4-pro":{"draws":2,"losses":2,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":5,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":15,"losses":17,"wins":16},"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":14,"losses":16,"wins":8},"google/gemini-3.8-flash":{"draws":6,"losses":7,"wins":1},"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":9},"gpt-5.6-luna":{"draws":12,"losses":2,"wins":14},"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":21,"losses":15,"wins":10},"gpt-6-sol":{"draws":10,"losses":25,"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":10,"losses":1,"wins":19},"meituan/longcat-2.0":{"draws":12,"losses":7,"wins":28},"meta/muse-glimmer-30b":{"draws":14,"losses":0,"wins":12},"meta/muse-spark-1.2":{"draws":5,"losses":5,"wins":14},"meta/muse-spark-1.3":{"draws":12,"losses":9,"wins":5},"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":12},"nex-agi/nex-n2-pro":{"draws":0,"losses":4,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":9,"losses":1,"wins":16},"o3":{"draws":4,"losses":7,"wins":15},"openai/gpt-oss-120b":{"draws":10,"losses":4,"wins":20},"poolside/laguna-s-2.1":{"draws":5,"losses":4,"wins":3},"qwen/qwen3.7-max":{"draws":6,"losses":1,"wins":3},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":10,"losses":7,"wins":11},"qwen/qwen3.8-27b":{"draws":0,"losses":6,"wins":4},"qwen/qwen3.8-flash":{"draws":7,"losses":8,"wins":5},"qwen/qwen3.8-max":{"draws":5,"losses":5,"wins":12},"qwen/qwen3.8-max-0902":{"draws":16,"losses":30,"wins":30},"stealth/ox-alpha":{"draws":21,"losses":34,"wins":35},"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":9,"losses":0,"wins":11},"thinkingmachines/inkling-small":{"draws":6,"losses":4,"wins":6},"x-ai/grok-4.5":{"draws":3,"losses":7,"wins":6},"x-ai/grok-4.6":{"draws":7,"losses":13,"wins":6},"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":11,"losses":28,"wins":21},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":12,"wins":13},"z-ai/glm-5.2":{"draws":15,"losses":3,"wins":24},"z-ai/glm-5.3":{"draws":11,"losses":11,"wins":4},"z-ai/glm-5.3-flash":{"draws":1,"losses":8,"wins":9},"z-ai/glm-5.3-flashx":{"draws":17,"losses":28,"wins":35}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":98,"losses":86,"wins":194},"claude-fable-5":{"draws":100,"losses":255,"wins":101},"claude-fable-5-1":{"draws":51,"losses":474,"wins":27},"claude-opus-4-5":{"draws":133,"losses":128,"wins":190},"claude-opus-4-8":{"draws":35,"losses":37,"wins":60},"claude-opus-5":{"draws":36,"losses":198,"wins":35},"claude-opus-5-5":{"draws":8,"losses":86,"wins":4},"claude-sonnet-5":{"draws":120,"losses":139,"wins":204},"cohere/north-mini-code":{"draws":10,"losses":11,"wins":35},"deepseek/deepseek-v4-flash":{"draws":152,"losses":104,"wins":203},"deepseek/deepseek-v4-pro":{"draws":130,"losses":139,"wins":153},"deepseek/deepseek-v4-pro-0813":{"draws":129,"losses":140,"wins":169},"deepseek/deepseek-v4.1-flash":{"draws":20,"losses":34,"wins":48},"google/gemini-3.1-flash-lite":{"draws":17,"losses":8,"wins":35},"google/gemini-3.5-flash":{"draws":115,"losses":174,"wins":190},"google/gemini-3.5-flash-lite":{"draws":202,"losses":166,"wins":375},"google/gemini-3.6-flash":{"draws":171,"losses":297,"wins":283},"google/gemini-3.8-flash":{"draws":113,"losses":216,"wins":155},"google/gemma-4-31b-it":{"draws":11,"losses":5,"wins":36},"gpt-4.1":{"draws":15,"losses":8,"wins":23},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":16},"gpt-5":{"draws":34,"losses":30,"wins":56},"gpt-5.4":{"draws":146,"losses":171,"wins":134},"gpt-5.4-mini":{"draws":24,"losses":26,"wins":44},"gpt-5.4-nano":{"draws":19,"losses":19,"wins":72},"gpt-5.5":{"draws":33,"losses":26,"wins":43},"gpt-5.6-luna":{"draws":143,"losses":99,"wins":161},"gpt-5.6-sol":{"draws":72,"losses":279,"wins":140},"gpt-5.6-terra":{"draws":145,"losses":120,"wins":161},"gpt-6-astra":{"draws":67,"losses":387,"wins":32},"gpt-6-luna":{"draws":18,"losses":18,"wins":22},"gpt-6-sol":{"draws":13,"losses":47,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":33,"losses":3,"wins":24},"inception/mercury-2.5-preview":{"draws":97,"losses":38,"wins":134},"inclusionai/ling-3.0-flash":{"draws":36,"losses":24,"wins":70},"meituan/longcat-2.0":{"draws":67,"losses":44,"wins":169},"meta/muse-glimmer-30b":{"draws":119,"losses":57,"wins":196},"meta/muse-spark-1.2":{"draws":89,"losses":105,"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":73,"losses":44,"wins":121},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":10,"wins":9},"moonshotai/kimi-k3":{"draws":113,"losses":135,"wins":173},"nex-agi/nex-n2-pro":{"draws":17,"losses":11,"wins":42},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":9,"wins":55},"o3":{"draws":51,"losses":179,"wins":208},"openai/gpt-oss-120b":{"draws":106,"losses":55,"wins":176},"poolside/laguna-s-2.1":{"draws":97,"losses":43,"wins":139},"qwen/qwen3.7-max":{"draws":14,"losses":20,"wins":42},"qwen/qwen3.7-plus":{"draws":11,"losses":7,"wins":34},"qwen/qwen3.8-2.4t-a95b":{"draws":135,"losses":158,"wins":169},"qwen/qwen3.8-27b":{"draws":61,"losses":92,"wins":112},"qwen/qwen3.8-flash":{"draws":88,"losses":83,"wins":106},"qwen/qwen3.8-max":{"draws":129,"losses":158,"wins":183},"qwen/qwen3.8-max-0902":{"draws":21,"losses":35,"wins":34},"stealth/ox-alpha":{"draws":386,"losses":676,"wins":676},"stepfun/step-3.7-flash":{"draws":18,"losses":24,"wins":66},"tencent/hy3-preview":{"draws":35,"losses":10,"wins":23},"tencent/hy4-preview":{"draws":107,"losses":202,"wins":148},"thinkingmachines/inkling":{"draws":84,"losses":60,"wins":195},"thinkingmachines/inkling-small":{"draws":161,"losses":70,"wins":219},"x-ai/grok-4.5":{"draws":76,"losses":148,"wins":102},"x-ai/grok-4.6":{"draws":141,"losses":193,"wins":162},"x-ai/grok-4.7":{"draws":5,"losses":27,"wins":8},"x-ai/grok-build-0.1":{"draws":13,"losses":6,"wins":25},"xiaomi/mimo-v2.5":{"draws":48,"losses":30,"wins":102},"xiaomi/mimo-v2.5-pro":{"draws":11,"losses":28,"wins":43},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":25,"wins":28},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":19,"wins":14},"z-ai/glm-5.2":{"draws":166,"losses":138,"wins":262},"z-ai/glm-5.3":{"draws":89,"losses":238,"wins":113},"z-ai/glm-5.3-flash":{"draws":118,"losses":188,"wins":179},"z-ai/glm-5.3-flashx":{"draws":15,"losses":43,"wins":38}},"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":36,"losses":80,"wins":24},"claude-opus-4-8":{"draws":16,"losses":42,"wins":14},"claude-opus-5":{"draws":11,"losses":66,"wins":1},"claude-opus-5-5":{"draws":2,"losses":20,"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":2},"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":10,"losses":23,"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":23,"losses":28,"wins":5},"gpt-5.4":{"draws":13,"losses":39,"wins":8},"gpt-5.4-mini":{"draws":20,"losses":8,"wins":8},"gpt-5.4-nano":{"draws":26,"losses":46,"wins":20},"gpt-5.5":{"draws":10,"losses":45,"wins":11},"gpt-5.6-luna":{"draws":20,"losses":20,"wins":26},"gpt-5.6-sol":{"draws":2,"losses":38,"wins":12},"gpt-5.6-terra":{"draws":11,"losses":18,"wins":7},"gpt-6-astra":{"draws":0,"losses":26,"wins":0},"gpt-6-luna":{"draws":4,"losses":7,"wins":5},"gpt-6-sol":{"draws":1,"losses":14,"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":18,"losses":10,"wins":26},"meituan/longcat-2.0":{"draws":23,"losses":40,"wins":47},"meta/muse-glimmer-30b":{"draws":14,"losses":17,"wins":5},"meta/muse-spark-1.2":{"draws":2,"losses":33,"wins":11},"meta/muse-spark-1.3":{"draws":8,"losses":34,"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":47,"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":103,"wins":50},"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":23,"wins":3},"qwen/qwen3.8-max-0902":{"draws":3,"losses":11,"wins":2},"stealth/ox-alpha":{"draws":18,"losses":66,"wins":24},"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":11},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":1,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"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":15,"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":26,"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":21,"losses":95,"wins":10},"claude-opus-5-5":{"draws":0,"losses":22,"wins":0},"claude-sonnet-5":{"draws":15,"losses":14,"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":31,"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":16,"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":11},"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":9,"losses":10,"wins":3},"gpt-6-astra":{"draws":1,"losses":11,"wins":0},"gpt-6-luna":{"draws":9,"losses":9,"wins":4},"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":7,"wins":4},"inclusionai/ling-3.0-flash":{"draws":15,"losses":5,"wins":22},"meituan/longcat-2.0":{"draws":28,"losses":22,"wins":22},"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":12,"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":9,"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":11},"x-ai/grok-4.5":{"draws":11,"losses":33,"wins":6},"x-ai/grok-4.6":{"draws":8,"losses":10,"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":4,"wins":0},"z-ai/glm-5.2":{"draws":41,"losses":33,"wins":26},"z-ai/glm-5.3":{"draws":1,"losses":10,"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":64},"claude-fable-5":{"draws":25,"losses":81,"wins":30},"claude-fable-5-1":{"draws":5,"losses":127,"wins":14},"claude-opus-4-5":{"draws":39,"losses":41,"wins":60},"claude-opus-4-8":{"draws":14,"losses":19,"wins":25},"claude-opus-5":{"draws":9,"losses":63,"wins":10},"claude-opus-5-5":{"draws":0,"losses":13,"wins":3},"claude-sonnet-5":{"draws":46,"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":16},"google/gemini-3.5-flash":{"draws":32,"losses":45,"wins":77},"google/gemini-3.5-flash-lite":{"draws":80,"losses":46,"wins":106},"google/gemini-3.6-flash":{"draws":56,"losses":105,"wins":93},"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":41},"gpt-5.4-mini":{"draws":11,"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":23,"losses":73,"wins":46},"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":7},"gpt-6-sol":{"draws":2,"losses":9,"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":10,"losses":6,"wins":26},"meituan/longcat-2.0":{"draws":22,"losses":13,"wins":47},"meta/muse-glimmer-30b":{"draws":42,"losses":13,"wins":49},"meta/muse-spark-1.2":{"draws":21,"losses":32,"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":16,"losses":3,"wins":17},"o3":{"draws":19,"losses":52,"wins":73},"openai/gpt-oss-120b":{"draws":34,"losses":18,"wins":34},"poolside/laguna-s-2.1":{"draws":41,"losses":15,"wins":36},"qwen/qwen3.7-max":{"draws":7,"losses":4,"wins":11},"qwen/qwen3.7-plus":{"draws":6,"losses":5,"wins":5},"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":107,"losses":148,"wins":202},"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":67},"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":51,"losses":35,"wins":74},"z-ai/glm-5.3":{"draws":19,"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":9}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":40,"losses":54,"wins":34},"claude-fable-5":{"draws":18,"losses":56,"wins":2},"claude-fable-5-1":{"draws":7,"losses":71,"wins":0},"claude-opus-4-5":{"draws":95,"losses":141,"wins":42},"claude-opus-4-8":{"draws":24,"losses":65,"wins":17},"claude-opus-5":{"draws":15,"losses":146,"wins":21},"claude-opus-5-5":{"draws":0,"losses":26,"wins":0},"claude-sonnet-5":{"draws":64,"losses":110,"wins":26},"cohere/north-mini-code":{"draws":15,"losses":25,"wins":22},"deepseek/deepseek-v4-flash":{"draws":57,"losses":54,"wins":53},"deepseek/deepseek-v4-pro":{"draws":34,"losses":45,"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":167,"losses":237,"wins":72},"google/gemini-3.8-flash":{"draws":31,"losses":49,"wins":8},"google/gemma-4-31b-it":{"draws":12,"losses":15,"wins":19},"gpt-4.1":{"draws":12,"losses":13,"wins":19},"gpt-4.1-nano":{"draws":0,"losses":12,"wins":0},"gpt-5":{"draws":30,"losses":40,"wins":24},"gpt-5.4":{"draws":41,"losses":80,"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":55,"wins":23},"gpt-5.6-luna":{"draws":74,"losses":89,"wins":43},"gpt-5.6-sol":{"draws":27,"losses":125,"wins":12},"gpt-5.6-terra":{"draws":30,"losses":51,"wins":17},"gpt-6-astra":{"draws":6,"losses":68,"wins":0},"gpt-6-luna":{"draws":11,"losses":8,"wins":1},"gpt-6-sol":{"draws":3,"losses":24,"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":50},"meituan/longcat-2.0":{"draws":54,"losses":68,"wins":90},"meta/muse-glimmer-30b":{"draws":44,"losses":34,"wins":28},"meta/muse-spark-1.2":{"draws":47,"losses":68,"wins":21},"meta/muse-spark-1.3":{"draws":23,"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":15,"losses":20,"wins":19},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":48,"losses":41,"wins":35},"o3":{"draws":61,"losses":162,"wins":64},"openai/gpt-oss-120b":{"draws":36,"losses":27,"wins":31},"poolside/laguna-s-2.1":{"draws":85,"losses":85,"wins":58},"qwen/qwen3.7-max":{"draws":31,"losses":35,"wins":12},"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":37,"wins":11},"qwen/qwen3.8-flash":{"draws":30,"losses":26,"wins":16},"qwen/qwen3.8-max":{"draws":38,"losses":41,"wins":21},"qwen/qwen3.8-max-0902":{"draws":9,"losses":11,"wins":0},"stealth/ox-alpha":{"draws":84,"losses":195,"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":36},"x-ai/grok-4.5":{"draws":71,"losses":111,"wins":32},"x-ai/grok-4.6":{"draws":26,"losses":35,"wins":7},"x-ai/grok-4.7":{"draws":2,"losses":8,"wins":0},"x-ai/grok-build-0.1":{"draws":18,"losses":11,"wins":11},"xiaomi/mimo-v2.5":{"draws":62,"losses":85,"wins":39},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":34,"wins":16},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":10,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":5,"wins":0},"z-ai/glm-5.2":{"draws":69,"losses":73,"wins":56},"z-ai/glm-5.3":{"draws":21,"losses":54,"wins":9},"z-ai/glm-5.3-flash":{"draws":28,"losses":48,"wins":14},"z-ai/glm-5.3-flashx":{"draws":11,"losses":17,"wins":2}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":56,"losses":55,"wins":27},"claude-fable-5":{"draws":28,"losses":62,"wins":12},"claude-fable-5-1":{"draws":8,"losses":109,"wins":1},"claude-opus-4-5":{"draws":48,"losses":71,"wins":22},"claude-opus-4-8":{"draws":8,"losses":16,"wins":2},"claude-opus-5":{"draws":3,"losses":45,"wins":4},"claude-opus-5-5":{"draws":6,"losses":18,"wins":0},"claude-sonnet-5":{"draws":47,"losses":87,"wins":26},"cohere/north-mini-code":{"draws":10,"losses":2,"wins":8},"deepseek/deepseek-v4-flash":{"draws":83,"losses":67,"wins":24},"deepseek/deepseek-v4-pro":{"draws":62,"losses":65,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":49,"losses":65,"wins":24},"deepseek/deepseek-v4.1-flash":{"draws":8,"losses":14,"wins":2},"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":102,"wins":91},"google/gemini-3.6-flash":{"draws":74,"losses":100,"wins":50},"google/gemini-3.8-flash":{"draws":47,"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":10,"losses":16,"wins":2},"gpt-5.4":{"draws":59,"losses":39,"wins":11},"gpt-5.4-mini":{"draws":12,"losses":3,"wins":5},"gpt-5.4-nano":{"draws":15,"losses":12,"wins":13},"gpt-5.5":{"draws":7,"losses":21,"wins":4},"gpt-5.6-luna":{"draws":68,"losses":50,"wins":52},"gpt-5.6-sol":{"draws":16,"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":18,"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":29,"losses":38,"wins":32},"meta/muse-glimmer-30b":{"draws":72,"losses":54,"wins":26},"meta/muse-spark-1.2":{"draws":32,"losses":54,"wins":24},"meta/muse-spark-1.3":{"draws":44,"losses":61,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":4,"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":9},"o3":{"draws":54,"losses":70,"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":5,"losses":11,"wins":10},"qwen/qwen3.7-plus":{"draws":6,"losses":8,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":46,"losses":79,"wins":17},"qwen/qwen3.8-27b":{"draws":20,"losses":54,"wins":12},"qwen/qwen3.8-flash":{"draws":45,"losses":31,"wins":16},"qwen/qwen3.8-max":{"draws":98,"losses":111,"wins":68},"qwen/qwen3.8-max-0902":{"draws":6,"losses":6,"wins":4},"stealth/ox-alpha":{"draws":161,"losses":219,"wins":70},"stepfun/step-3.7-flash":{"draws":15,"losses":13,"wins":16},"tencent/hy3-preview":{"draws":20,"losses":11,"wins":5},"tencent/hy4-preview":{"draws":48,"losses":67,"wins":17},"thinkingmachines/inkling":{"draws":41,"losses":36,"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":10,"wins":0},"x-ai/grok-build-0.1":{"draws":6,"losses":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":26,"losses":9,"wins":15},"xiaomi/mimo-v2.5-pro":{"draws":12,"losses":6,"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":77,"losses":73,"wins":44},"z-ai/glm-5.3":{"draws":24,"losses":64,"wins":12},"z-ai/glm-5.3-flash":{"draws":55,"losses":70,"wins":25},"z-ai/glm-5.3-flashx":{"draws":3,"losses":8,"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":52,"wins":38},"claude-fable-5-1":{"draws":1,"losses":95,"wins":10},"claude-opus-4-5":{"draws":86,"losses":71,"wins":127},"claude-opus-4-8":{"draws":28,"losses":37,"wins":43},"claude-opus-5":{"draws":33,"losses":148,"wins":45},"claude-opus-5-5":{"draws":4,"losses":33,"wins":7},"claude-sonnet-5":{"draws":69,"losses":42,"wins":99},"cohere/north-mini-code":{"draws":9,"losses":4,"wins":31},"deepseek/deepseek-v4-flash":{"draws":29,"losses":24,"wins":69},"deepseek/deepseek-v4-pro":{"draws":26,"losses":38,"wins":34},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":35,"wins":33},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":1,"wins":10},"google/gemini-3.1-flash-lite":{"draws":13,"losses":1,"wins":38},"google/gemini-3.5-flash":{"draws":29,"losses":35,"wins":48},"google/gemini-3.5-flash-lite":{"draws":122,"losses":96,"wins":254},"google/gemini-3.6-flash":{"draws":98,"losses":206,"wins":190},"google/gemini-3.8-flash":{"draws":22,"losses":35,"wins":61},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":16},"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":91,"wins":69},"gpt-5.4-mini":{"draws":19,"losses":5,"wins":26},"gpt-5.4-nano":{"draws":12,"losses":29,"wins":45},"gpt-5.5":{"draws":31,"losses":26,"wins":41},"gpt-5.6-luna":{"draws":47,"losses":68,"wins":83},"gpt-5.6-sol":{"draws":27,"losses":121,"wins":78},"gpt-5.6-terra":{"draws":32,"losses":26,"wins":70},"gpt-6-astra":{"draws":6,"losses":99,"wins":11},"gpt-6-luna":{"draws":5,"losses":6,"wins":9},"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":40,"losses":15,"wins":87},"meituan/longcat-2.0":{"draws":51,"losses":43,"wins":130},"meta/muse-glimmer-30b":{"draws":27,"losses":12,"wins":45},"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":32},"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":85,"losses":82,"wins":107},"nex-agi/nex-n2-pro":{"draws":16,"losses":1,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":21,"losses":2,"wins":43},"o3":{"draws":24,"losses":83,"wins":169},"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":18,"losses":14,"wins":22},"qwen/qwen3.7-plus":{"draws":13,"losses":8,"wins":25},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":33,"wins":49},"qwen/qwen3.8-27b":{"draws":7,"losses":33,"wins":32},"qwen/qwen3.8-flash":{"draws":14,"losses":13,"wins":31},"qwen/qwen3.8-max":{"draws":33,"losses":37,"wins":43},"qwen/qwen3.8-max-0902":{"draws":3,"losses":6,"wins":7},"stealth/ox-alpha":{"draws":76,"losses":102,"wins":148},"stepfun/step-3.7-flash":{"draws":13,"losses":15,"wins":54},"tencent/hy3-preview":{"draws":11,"losses":6,"wins":33},"tencent/hy4-preview":{"draws":27,"losses":44,"wins":37},"thinkingmachines/inkling":{"draws":71,"losses":32,"wins":111},"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":10,"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":4},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":11,"wins":5},"z-ai/glm-5.2":{"draws":45,"losses":53,"wins":82},"z-ai/glm-5.3":{"draws":28,"losses":57,"wins":21},"z-ai/glm-5.3-flash":{"draws":17,"losses":44,"wins":29},"z-ai/glm-5.3-flashx":{"draws":2,"losses":8,"wins":6}},"x-ai/grok-4.6":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":19,"wins":48},"claude-fable-5":{"draws":39,"losses":75,"wins":54},"claude-fable-5-1":{"draws":11,"losses":147,"wins":24},"claude-opus-4-5":{"draws":43,"losses":23,"wins":76},"claude-opus-4-8":{"draws":8,"losses":17,"wins":19},"claude-opus-5":{"draws":9,"losses":57,"wins":15},"claude-opus-5-5":{"draws":2,"losses":26,"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":47,"losses":17,"wins":94},"deepseek/deepseek-v4-pro":{"draws":35,"losses":33,"wins":60},"deepseek/deepseek-v4-pro-0813":{"draws":53,"losses":36,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":13,"losses":6,"wins":13},"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":120},"google/gemini-3.6-flash":{"draws":59,"losses":68,"wins":87},"google/gemini-3.8-flash":{"draws":43,"losses":51,"wins":54},"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":7,"losses":4,"wins":21},"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":65},"gpt-5.6-sol":{"draws":31,"losses":68,"wins":67},"gpt-5.6-terra":{"draws":48,"losses":25,"wins":79},"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":4,"losses":0,"wins":10},"inception/mercury-2.5-preview":{"draws":31,"losses":12,"wins":33},"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":38},"meta/muse-spark-1.2":{"draws":23,"losses":21,"wins":60},"meta/muse-spark-1.3":{"draws":31,"losses":52,"wins":57},"minimax/minimax-m3":{"draws":5,"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":57},"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":75},"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":43,"losses":45,"wins":56},"qwen/qwen3.8-27b":{"draws":19,"losses":26,"wins":29},"qwen/qwen3.8-flash":{"draws":33,"losses":18,"wins":35},"qwen/qwen3.8-max":{"draws":41,"losses":47,"wins":66},"qwen/qwen3.8-max-0902":{"draws":7,"losses":6,"wins":13},"stealth/ox-alpha":{"draws":141,"losses":162,"wins":193},"stepfun/step-3.7-flash":{"draws":7,"losses":7,"wins":18},"tencent/hy3-preview":{"draws":8,"losses":4,"wins":10},"tencent/hy4-preview":{"draws":42,"losses":41,"wins":57},"thinkingmachines/inkling":{"draws":26,"losses":7,"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":32},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":7,"wins":22},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":2,"wins":10},"xiaomi/mimo-v2.6-pro":{"draws":5,"losses":10,"wins":5},"z-ai/glm-5.2":{"draws":46,"losses":30,"wins":78},"z-ai/glm-5.3":{"draws":30,"losses":70,"wins":48},"z-ai/glm-5.3-flash":{"draws":34,"losses":55,"wins":51},"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":9,"wins":12},"claude-fable-5-1":{"draws":1,"losses":15,"wins":0},"claude-opus-4-5":{"draws":3,"losses":6,"wins":15},"claude-opus-4-8":{"draws":4,"losses":5,"wins":7},"claude-opus-5":{"draws":3,"losses":13,"wins":8},"claude-opus-5-5":{"draws":4,"losses":61,"wins":19},"claude-sonnet-5":{"draws":2,"losses":4,"wins":12},"cohere/north-mini-code":{"draws":1,"losses":0,"wins":5},"deepseek/deepseek-v4-flash":{"draws":2,"losses":1,"wins":21},"deepseek/deepseek-v4-pro":{"draws":2,"losses":4,"wins":10},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":2,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":4,"wins":6},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":11},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":16},"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":13},"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":9,"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":4},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":14},"minimax/minimax-m3":{"draws":0,"losses":0,"wins":4},"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":2,"wins":8},"qwen/qwen3.7-max":{"draws":1,"losses":2,"wins":9},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":7,"wins":13},"qwen/qwen3.8-27b":{"draws":0,"losses":2,"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":5,"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":2,"losses":0,"wins":8},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":10},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":10},"x-ai/grok-4.6":{"draws":3,"losses":6,"wins":11},"x-ai/grok-4.7":{"draws":0,"losses":12,"wins":12},"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":8,"losses":11,"wins":25},"z-ai/glm-5.2":{"draws":3,"losses":5,"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":16,"wins":33}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":7,"wins":2},"claude-fable-5":{"draws":2,"losses":10,"wins":4},"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":37,"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":6,"losses":4,"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":3,"wins":1},"gpt-5.4-mini":{"draws":26,"losses":18,"wins":12},"gpt-5.4-nano":{"draws":13,"losses":35,"wins":16},"gpt-5.5":{"draws":32,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":8,"wins":4},"gpt-6-astra":{"draws":1,"losses":11,"wins":0},"gpt-6-luna":{"draws":7,"losses":5,"wins":0},"gpt-6-sol":{"draws":3,"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":10,"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":43,"losses":9,"wins":8},"o3":{"draws":8,"losses":20,"wins":2},"openai/gpt-oss-120b":{"draws":2,"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":1,"wins":1},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":13,"losses":25,"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":2,"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":19,"losses":18,"wins":11},"claude-fable-5":{"draws":13,"losses":43,"wins":2},"claude-fable-5-1":{"draws":2,"losses":62,"wins":0},"claude-opus-4-5":{"draws":141,"losses":135,"wins":60},"claude-opus-4-8":{"draws":69,"losses":116,"wins":21},"claude-opus-5":{"draws":48,"losses":196,"wins":16},"claude-opus-5-5":{"draws":4,"losses":40,"wins":0},"claude-sonnet-5":{"draws":26,"losses":26,"wins":2},"cohere/north-mini-code":{"draws":46,"losses":29,"wins":39},"deepseek/deepseek-v4-flash":{"draws":93,"losses":58,"wins":83},"deepseek/deepseek-v4-pro":{"draws":18,"losses":20,"wins":6},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":19,"wins":10},"deepseek/deepseek-v4.1-flash":{"draws":18,"losses":28,"wins":2},"google/gemini-3.1-flash-lite":{"draws":66,"losses":45,"wins":77},"google/gemini-3.5-flash":{"draws":24,"losses":29,"wins":17},"google/gemini-3.5-flash-lite":{"draws":53,"losses":41,"wins":42},"google/gemini-3.6-flash":{"draws":68,"losses":82,"wins":30},"google/gemini-3.8-flash":{"draws":24,"losses":28,"wins":6},"google/gemma-4-31b-it":{"draws":35,"losses":51,"wins":52},"gpt-4.1":{"draws":38,"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":18,"losses":19,"wins":3},"gpt-5.4-mini":{"draws":80,"losses":51,"wins":43},"gpt-5.4-nano":{"draws":71,"losses":121,"wins":106},"gpt-5.5":{"draws":92,"losses":80,"wins":22},"gpt-5.6-luna":{"draws":35,"losses":16,"wins":5},"gpt-5.6-sol":{"draws":5,"losses":41,"wins":2},"gpt-5.6-terra":{"draws":19,"losses":38,"wins":5},"gpt-6-astra":{"draws":1,"losses":41,"wins":0},"gpt-6-luna":{"draws":17,"losses":13,"wins":10},"gpt-6-sol":{"draws":6,"losses":27,"wins":1},"ibm-granite/granite-4.2-8b":{"draws":4,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":22,"losses":5,"wins":15},"inclusionai/ling-3.0-flash":{"draws":56,"losses":28,"wins":44},"meituan/longcat-2.0":{"draws":71,"losses":72,"wins":63},"meta/muse-glimmer-30b":{"draws":30,"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":8,"losses":10,"wins":6},"moonshotai/kimi-k2.7-code":{"draws":33,"losses":42,"wins":13},"moonshotai/kimi-k3":{"draws":28,"losses":60,"wins":12},"nex-agi/nex-n2-pro":{"draws":31,"losses":35,"wins":50},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":110,"losses":69,"wins":57},"o3":{"draws":37,"losses":77,"wins":20},"openai/gpt-oss-120b":{"draws":31,"losses":17,"wins":16},"poolside/laguna-s-2.1":{"draws":54,"losses":52,"wins":42},"qwen/qwen3.7-max":{"draws":66,"losses":68,"wins":28},"qwen/qwen3.7-plus":{"draws":57,"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":28,"wins":7},"qwen/qwen3.8-max-0902":{"draws":24,"losses":22,"wins":4},"stealth/ox-alpha":{"draws":48,"losses":102,"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":85},"thinkingmachines/inkling-small":{"draws":26,"losses":15,"wins":9},"x-ai/grok-4.5":{"draws":43,"losses":58,"wins":15},"x-ai/grok-4.6":{"draws":28,"losses":32,"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":188,"losses":116,"wins":116},"xiaomi/mimo-v2.5-pro":{"draws":46,"losses":61,"wins":31},"xiaomi/mimo-v2.6-flash":{"draws":7,"losses":25,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":8,"wins":1},"z-ai/glm-5.2":{"draws":115,"losses":109,"wins":58},"z-ai/glm-5.3":{"draws":15,"losses":27,"wins":0},"z-ai/glm-5.3-flash":{"draws":12,"losses":33,"wins":13},"z-ai/glm-5.3-flashx":{"draws":16,"losses":18,"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":0},"claude-fable-5-1":{"draws":0,"losses":22,"wins":0},"claude-opus-4-5":{"draws":25,"losses":49,"wins":44},"claude-opus-4-8":{"draws":20,"losses":38,"wins":22},"claude-opus-5":{"draws":17,"losses":81,"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":19,"wins":26},"deepseek/deepseek-v4-pro":{"draws":7,"losses":14,"wins":9},"deepseek/deepseek-v4-pro-0813":{"draws":8,"losses":17,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":6,"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":21,"losses":33,"wins":22},"google/gemini-3.8-flash":{"draws":11,"losses":15,"wins":6},"google/gemma-4-31b-it":{"draws":6,"losses":7,"wins":17},"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":19},"gpt-5.4":{"draws":8,"losses":31,"wins":5},"gpt-5.4-mini":{"draws":9,"losses":22,"wins":17},"gpt-5.4-nano":{"draws":23,"losses":32,"wins":47},"gpt-5.5":{"draws":17,"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":10,"wins":4},"gpt-6-astra":{"draws":2,"losses":26,"wins":2},"gpt-6-luna":{"draws":6,"losses":4,"wins":0},"gpt-6-sol":{"draws":0,"losses":4,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":8,"losses":7,"wins":7},"inclusionai/ling-3.0-flash":{"draws":21,"losses":15,"wins":26},"meituan/longcat-2.0":{"draws":30,"losses":24,"wins":34},"meta/muse-glimmer-30b":{"draws":7,"losses":8,"wins":7},"meta/muse-spark-1.2":{"draws":5,"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":7},"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":24},"o3":{"draws":14,"losses":25,"wins":43},"openai/gpt-oss-120b":{"draws":8,"losses":4,"wins":8},"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":17,"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":7},"qwen/qwen3.8-max-0902":{"draws":3,"losses":6,"wins":5},"stealth/ox-alpha":{"draws":11,"losses":43,"wins":28},"stepfun/step-3.7-flash":{"draws":12,"losses":11,"wins":23},"tencent/hy3-preview":{"draws":16,"losses":21,"wins":15},"tencent/hy4-preview":{"draws":2,"losses":14,"wins":4},"thinkingmachines/inkling":{"draws":12,"losses":16,"wins":34},"thinkingmachines/inkling-small":{"draws":12,"losses":4,"wins":6},"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":61},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"wins":4},"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":39,"losses":42,"wins":35},"z-ai/glm-5.3":{"draws":10,"losses":20,"wins":4},"z-ai/glm-5.3-flash":{"draws":9,"losses":14,"wins":5},"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":1,"losses":22,"wins":5},"claude-opus-4-5":{"draws":4,"losses":6,"wins":6},"claude-opus-4-8":{"draws":3,"losses":3,"wins":8},"claude-opus-5":{"draws":1,"losses":13,"wins":2},"claude-opus-5-5":{"draws":4,"losses":51,"wins":1},"claude-sonnet-5":{"draws":7,"losses":4,"wins":9},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":11},"deepseek/deepseek-v4-flash":{"draws":11,"losses":3,"wins":18},"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":7,"wins":6},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":3,"losses":4,"wins":7},"google/gemini-3.5-flash-lite":{"draws":5,"losses":3,"wins":10},"google/gemini-3.6-flash":{"draws":3,"losses":17,"wins":14},"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":3},"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":7,"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":9,"losses":43,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":4},"inclusionai/ling-3.0-flash":{"draws":1,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":2,"wins":1},"meta/muse-glimmer-30b":{"draws":3,"losses":3,"wins":6},"meta/muse-spark-1.2":{"draws":1,"losses":9,"wins":2},"meta/muse-spark-1.3":{"draws":6,"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":7,"wins":18},"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":6,"losses":4,"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":11,"losses":21,"wins":28},"stealth/ox-alpha":{"draws":7,"losses":28,"wins":25},"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":10},"thinkingmachines/inkling-small":{"draws":6,"losses":1,"wins":15},"x-ai/grok-4.5":{"draws":1,"losses":4,"wins":3},"x-ai/grok-4.6":{"draws":2,"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":2,"wins":25},"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":7},"z-ai/glm-5.2":{"draws":9,"losses":5,"wins":8},"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":28}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":7,"wins":12},"claude-fable-5":{"draws":1,"losses":13,"wins":4},"claude-fable-5-1":{"draws":1,"losses":13,"wins":4},"claude-opus-4-5":{"draws":0,"losses":2,"wins":12},"claude-opus-4-8":{"draws":0,"losses":8,"wins":6},"claude-opus-5":{"draws":5,"losses":6,"wins":5},"claude-opus-5-5":{"draws":15,"losses":48,"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":0,"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":3,"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":2,"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":5,"wins":9},"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":0,"wins":6},"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":3,"wins":5},"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":1,"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":5,"losses":9,"wins":4},"qwen/qwen3.8-max-0902":{"draws":9,"losses":13,"wins":12},"stealth/ox-alpha":{"draws":9,"losses":14,"wins":19},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":8},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":4},"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":5,"wins":11},"x-ai/grok-4.6":{"draws":5,"losses":5,"wins":10},"x-ai/grok-4.7":{"draws":8,"losses":25,"wins":11},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":1,"losses":1,"wins":8},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":2,"wins":1},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":7,"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":3,"losses":6,"wins":7},"z-ai/glm-5.3-flash":{"draws":1,"losses":3,"wins":0},"z-ai/glm-5.3-flashx":{"draws":10,"losses":23,"wins":27}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":78,"losses":53,"wins":49},"claude-fable-5":{"draws":45,"losses":73,"wins":28},"claude-fable-5-1":{"draws":16,"losses":107,"wins":3},"claude-opus-4-5":{"draws":104,"losses":143,"wins":93},"claude-opus-4-8":{"draws":66,"losses":91,"wins":53},"claude-opus-5":{"draws":53,"losses":179,"wins":22},"claude-opus-5-5":{"draws":3,"losses":51,"wins":2},"claude-sonnet-5":{"draws":62,"losses":78,"wins":54},"cohere/north-mini-code":{"draws":21,"losses":14,"wins":45},"deepseek/deepseek-v4-flash":{"draws":101,"losses":60,"wins":103},"deepseek/deepseek-v4-pro":{"draws":58,"losses":63,"wins":59},"deepseek/deepseek-v4-pro-0813":{"draws":58,"losses":71,"wins":51},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":19,"wins":14},"google/gemini-3.1-flash-lite":{"draws":38,"losses":19,"wins":73},"google/gemini-3.5-flash":{"draws":66,"losses":72,"wins":72},"google/gemini-3.5-flash-lite":{"draws":137,"losses":102,"wins":111},"google/gemini-3.6-flash":{"draws":91,"losses":120,"wins":87},"google/gemini-3.8-flash":{"draws":46,"losses":90,"wins":40},"google/gemma-4-31b-it":{"draws":28,"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":48,"wins":47},"gpt-5.4":{"draws":58,"losses":62,"wins":36},"gpt-5.4-mini":{"draws":71,"losses":17,"wins":40},"gpt-5.4-nano":{"draws":55,"losses":60,"wins":67},"gpt-5.5":{"draws":70,"losses":75,"wins":35},"gpt-5.6-luna":{"draws":73,"losses":37,"wins":60},"gpt-5.6-sol":{"draws":19,"losses":115,"wins":30},"gpt-5.6-terra":{"draws":86,"losses":68,"wins":40},"gpt-6-astra":{"draws":11,"losses":117,"wins":4},"gpt-6-luna":{"draws":12,"losses":13,"wins":19},"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":62,"losses":60,"wins":82},"meta/muse-glimmer-30b":{"draws":74,"losses":33,"wins":59},"meta/muse-spark-1.2":{"draws":30,"losses":64,"wins":52},"meta/muse-spark-1.3":{"draws":34,"losses":51,"wins":37},"minimax/minimax-m3":{"draws":37,"losses":19,"wins":32},"mistralai/mistral-medium-3-5":{"draws":50,"losses":19,"wins":53},"moonshotai/kimi-k2.7-code":{"draws":10,"losses":19,"wins":19},"moonshotai/kimi-k3":{"draws":67,"losses":51,"wins":34},"nex-agi/nex-n2-pro":{"draws":44,"losses":15,"wins":35},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":90,"losses":29,"wins":51},"o3":{"draws":38,"losses":95,"wins":89},"openai/gpt-oss-120b":{"draws":70,"losses":32,"wins":60},"poolside/laguna-s-2.1":{"draws":109,"losses":47,"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":63,"wins":52},"qwen/qwen3.8-27b":{"draws":35,"losses":45,"wins":38},"qwen/qwen3.8-flash":{"draws":47,"losses":44,"wins":25},"qwen/qwen3.8-max":{"draws":64,"losses":53,"wins":43},"qwen/qwen3.8-max-0902":{"draws":15,"losses":24,"wins":3},"stealth/ox-alpha":{"draws":166,"losses":262,"wins":138},"stepfun/step-3.7-flash":{"draws":26,"losses":23,"wins":47},"tencent/hy3-preview":{"draws":41,"losses":26,"wins":33},"tencent/hy4-preview":{"draws":51,"losses":74,"wins":35},"thinkingmachines/inkling":{"draws":69,"losses":56,"wins":73},"thinkingmachines/inkling-small":{"draws":77,"losses":44,"wins":73},"x-ai/grok-4.5":{"draws":45,"losses":82,"wins":53},"x-ai/grok-4.6":{"draws":46,"losses":78,"wins":30},"x-ai/grok-4.7":{"draws":3,"losses":18,"wins":5},"x-ai/grok-build-0.1":{"draws":11,"losses":6,"wins":17},"xiaomi/mimo-v2.5":{"draws":115,"losses":58,"wins":109},"xiaomi/mimo-v2.5-pro":{"draws":39,"losses":35,"wins":42},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":8,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":8,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":112,"losses":86,"wins":86},"z-ai/glm-5.3":{"draws":46,"losses":77,"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":11}},"z-ai/glm-5.3":{"bytedance-seed/seed-2.0-code":{"draws":25,"losses":13,"wins":56},"claude-fable-5":{"draws":22,"losses":53,"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":8,"losses":11,"wins":19},"claude-opus-5":{"draws":15,"losses":47,"wins":20},"claude-opus-5-5":{"draws":1,"losses":21,"wins":4},"claude-sonnet-5":{"draws":25,"losses":16,"wins":105},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":8},"deepseek/deepseek-v4-flash":{"draws":36,"losses":7,"wins":73},"deepseek/deepseek-v4-pro":{"draws":23,"losses":22,"wins":73},"deepseek/deepseek-v4-pro-0813":{"draws":26,"losses":25,"wins":65},"deepseek/deepseek-v4.1-flash":{"draws":9,"losses":8,"wins":13},"google/gemini-3.1-flash-lite":{"draws":5,"losses":1,"wins":16},"google/gemini-3.5-flash":{"draws":25,"losses":33,"wins":82},"google/gemini-3.5-flash-lite":{"draws":44,"losses":17,"wins":151},"google/gemini-3.6-flash":{"draws":33,"losses":43,"wins":136},"google/gemini-3.8-flash":{"draws":23,"losses":39,"wins":88},"google/gemma-4-31b-it":{"draws":1,"losses":1,"wins":12},"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":56,"wins":71},"gpt-5.4-mini":{"draws":7,"losses":1,"wins":22},"gpt-5.4-nano":{"draws":7,"losses":12,"wins":29},"gpt-5.5":{"draws":8,"losses":10,"wins":16},"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":3,"losses":2,"wins":11},"gpt-6-sol":{"draws":6,"losses":10,"wins":12},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":4},"inception/mercury-2.5-preview":{"draws":30,"losses":4,"wins":32},"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":73},"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":29,"losses":27,"wins":70},"nex-agi/nex-n2-pro":{"draws":3,"losses":1,"wins":16},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":7,"wins":23},"o3":{"draws":9,"losses":27,"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":40},"qwen/qwen3.8-flash":{"draws":24,"losses":13,"wins":55},"qwen/qwen3.8-max":{"draws":31,"losses":27,"wins":66},"qwen/qwen3.8-max-0902":{"draws":11,"losses":4,"wins":11},"stealth/ox-alpha":{"draws":89,"losses":113,"wins":238},"stepfun/step-3.7-flash":{"draws":10,"losses":2,"wins":24},"tencent/hy3-preview":{"draws":1,"losses":3,"wins":10},"tencent/hy4-preview":{"draws":19,"losses":26,"wins":89},"thinkingmachines/inkling":{"draws":21,"losses":9,"wins":54},"thinkingmachines/inkling-small":{"draws":24,"losses":12,"wins":64},"x-ai/grok-4.5":{"draws":28,"losses":21,"wins":57},"x-ai/grok-4.6":{"draws":30,"losses":48,"wins":70},"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":3,"losses":7,"wins":6},"z-ai/glm-5.2":{"draws":46,"losses":25,"wins":77},"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":5,"losses":2,"wins":21}},"z-ai/glm-5.3-flash":{"bytedance-seed/seed-2.0-code":{"draws":35,"losses":16,"wins":53},"claude-fable-5":{"draws":25,"losses":73,"wins":44},"claude-fable-5-1":{"draws":16,"losses":135,"wins":17},"claude-opus-4-5":{"draws":38,"losses":36,"wins":72},"claude-opus-4-8":{"draws":8,"losses":14,"wins":16},"claude-opus-5":{"draws":8,"losses":76,"wins":20},"claude-opus-5-5":{"draws":6,"losses":26,"wins":0},"claude-sonnet-5":{"draws":31,"losses":37,"wins":76},"cohere/north-mini-code":{"draws":4,"losses":0,"wins":18},"deepseek/deepseek-v4-flash":{"draws":40,"losses":26,"wins":56},"deepseek/deepseek-v4-pro":{"draws":40,"losses":36,"wins":54},"deepseek/deepseek-v4-pro-0813":{"draws":37,"losses":38,"wins":55},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":11,"wins":6},"google/gemini-3.1-flash-lite":{"draws":1,"losses":4,"wins":13},"google/gemini-3.5-flash":{"draws":46,"losses":54,"wins":52},"google/gemini-3.5-flash-lite":{"draws":65,"losses":40,"wins":117},"google/gemini-3.6-flash":{"draws":54,"losses":70,"wins":96},"google/gemini-3.8-flash":{"draws":39,"losses":67,"wins":50},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":16},"gpt-4.1":{"draws":1,"losses":0,"wins":5},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":18,"losses":10,"wins":16},"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":73,"wins":57},"gpt-5.6-terra":{"draws":37,"losses":33,"wins":60},"gpt-6-astra":{"draws":24,"losses":117,"wins":9},"gpt-6-luna":{"draws":4,"losses":3,"wins":13},"gpt-6-sol":{"draws":5,"losses":15,"wins":8},"ibm-granite/granite-4.2-8b":{"draws":6,"losses":0,"wins":2},"inception/mercury-2.5-preview":{"draws":35,"losses":10,"wins":39},"inclusionai/ling-3.0-flash":{"draws":9,"losses":6,"wins":25},"meituan/longcat-2.0":{"draws":23,"losses":22,"wins":43},"meta/muse-glimmer-30b":{"draws":40,"losses":13,"wins":59},"meta/muse-spark-1.2":{"draws":16,"losses":37,"wins":45},"meta/muse-spark-1.3":{"draws":28,"losses":43,"wins":55},"minimax/minimax-m3":{"draws":7,"losses":3,"wins":8},"mistralai/mistral-medium-3-5":{"draws":23,"losses":14,"wins":29},"moonshotai/kimi-k3":{"draws":47,"losses":33,"wins":50},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":7,"losses":3,"wins":14},"o3":{"draws":29,"losses":58,"wins":61},"openai/gpt-oss-120b":{"draws":34,"losses":9,"wins":57},"poolside/laguna-s-2.1":{"draws":42,"losses":14,"wins":44},"qwen/qwen3.7-max":{"draws":6,"losses":4,"wins":10},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":37,"losses":52,"wins":47},"qwen/qwen3.8-27b":{"draws":25,"losses":31,"wins":34},"qwen/qwen3.8-flash":{"draws":29,"losses":31,"wins":24},"qwen/qwen3.8-max":{"draws":42,"losses":53,"wins":45},"qwen/qwen3.8-max-0902":{"draws":1,"losses":9,"wins":8},"stealth/ox-alpha":{"draws":118,"losses":179,"wins":188},"stepfun/step-3.7-flash":{"draws":15,"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":17,"losses":29,"wins":44},"x-ai/grok-4.6":{"draws":34,"losses":51,"wins":55},"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":33},"xiaomi/mimo-v2.5-pro":{"draws":9,"losses":5,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":5,"losses":6,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":1,"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":2,"wins":11}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":2,"wins":13},"claude-fable-5":{"draws":6,"losses":9,"wins":11},"claude-fable-5-1":{"draws":4,"losses":33,"wins":3},"claude-opus-4-5":{"draws":5,"losses":0,"wins":13},"claude-opus-4-8":{"draws":4,"losses":9,"wins":7},"claude-opus-5":{"draws":4,"losses":24,"wins":6},"claude-opus-5-5":{"draws":14,"losses":96,"wins":8},"claude-sonnet-5":{"draws":9,"losses":8,"wins":3},"cohere/north-mini-code":{"draws":1,"losses":1,"wins":6},"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":14,"losses":9,"wins":19},"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":28},"google/gemini-3.6-flash":{"draws":15,"losses":13,"wins":12},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":8},"google/gemma-4-31b-it":{"draws":2,"losses":0,"wins":6},"gpt-4.1":{"draws":8,"losses":3,"wins":7},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":12,"losses":2,"wins":6},"gpt-5.4":{"draws":7,"losses":4,"wins":7},"gpt-5.4-mini":{"draws":3,"losses":5,"wins":14},"gpt-5.4-nano":{"draws":8,"losses":8,"wins":16},"gpt-5.5":{"draws":16,"losses":8,"wins":4},"gpt-5.6-luna":{"draws":2,"losses":4,"wins":8},"gpt-5.6-sol":{"draws":7,"losses":6,"wins":5},"gpt-5.6-terra":{"draws":5,"losses":10,"wins":5},"gpt-6-astra":{"draws":2,"losses":20,"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":5,"losses":2,"wins":17},"meituan/longcat-2.0":{"draws":15,"losses":5,"wins":11},"meta/muse-glimmer-30b":{"draws":9,"losses":4,"wins":7},"meta/muse-spark-1.2":{"draws":3,"losses":10,"wins":7},"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":9},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":6,"losses":4,"wins":12},"o3":{"draws":1,"losses":12,"wins":29},"openai/gpt-oss-120b":{"draws":8,"losses":2,"wins":12},"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":7,"losses":9,"wins":14},"qwen/qwen3.8-27b":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.8-flash":{"draws":6,"losses":7,"wins":11},"qwen/qwen3.8-max":{"draws":14,"losses":6,"wins":4},"qwen/qwen3.8-max-0902":{"draws":17,"losses":35,"wins":28},"stealth/ox-alpha":{"draws":15,"losses":38,"wins":43},"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":9,"wins":6},"thinkingmachines/inkling":{"draws":11,"losses":2,"wins":17},"thinkingmachines/inkling-small":{"draws":3,"losses":3,"wins":8},"x-ai/grok-4.5":{"draws":2,"losses":6,"wins":8},"x-ai/grok-4.6":{"draws":14,"losses":9,"wins":3},"x-ai/grok-4.7":{"draws":9,"losses":33,"wins":16},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":16,"losses":2,"wins":18},"xiaomi/mimo-v2.5-pro":{"draws":3,"losses":0,"wins":5},"xiaomi/mimo-v2.6-flash":{"draws":15,"losses":28,"wins":31},"xiaomi/mimo-v2.6-pro":{"draws":10,"losses":27,"wins":23},"z-ai/glm-5.2":{"draws":9,"losses":11,"wins":14},"z-ai/glm-5.3":{"draws":5,"losses":21,"wins":2},"z-ai/glm-5.3-flash":{"draws":5,"losses":11,"wins":2},"z-ai/glm-5.3-flashx":{"draws":16,"losses":24,"wins":24}}},"versus_totals_tracks":{"highest":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":13,"losses":11,"wins":12},"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":23,"wins":21},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":18,"wins":13},"deepseek/deepseek-v4.1-flash":{"draws":4,"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":11},"google/gemini-3.5-flash-lite":{"draws":40,"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":14,"wins":9},"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":7,"wins":14},"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":16},"meta/muse-spark-1.2":{"draws":10,"losses":11,"wins":9},"meta/muse-spark-1.3":{"draws":12,"losses":18,"wins":6},"minimax/minimax-m3":{"draws":4,"losses":0,"wins":8},"mistralai/mistral-medium-3-5":{"draws":12,"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":24,"losses":6,"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":3,"wins":0},"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":21},"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":3},"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":26},"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":4,"wins":43},"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":9},"inclusionai/ling-3.0-flash":{"draws":0,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":2,"losses":7,"wins":14},"meta/muse-glimmer-30b":{"draws":4,"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":9},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":1,"wins":0},"moonshotai/kimi-k3":{"draws":4,"losses":5,"wins":25},"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":28},"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":10,"losses":3,"wins":15},"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":28,"losses":26,"wins":106},"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":2,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":12},"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":8,"losses":4,"wins":26},"z-ai/glm-5.3":{"draws":8,"losses":18,"wins":26},"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":61},"claude-fable-5-1":{"draws":4,"losses":19,"wins":53},"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":67},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"deepseek/deepseek-v4-flash":{"draws":0,"losses":0,"wins":46},"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":4},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":52},"google/gemini-3.5-flash-lite":{"draws":0,"losses":1,"wins":77},"google/gemini-3.6-flash":{"draws":6,"losses":5,"wins":77},"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":14},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":44},"gpt-5.6-sol":{"draws":2,"losses":7,"wins":65},"gpt-5.6-terra":{"draws":0,"losses":0,"wins":60},"gpt-6-astra":{"draws":5,"losses":31,"wins":44},"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":18},"meituan/longcat-2.0":{"draws":0,"losses":2,"wins":16},"meta/muse-glimmer-30b":{"draws":0,"losses":0,"wins":28},"meta/muse-spark-1.2":{"draws":1,"losses":3,"wins":36},"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":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":20},"o3":{"draws":0,"losses":0,"wins":46},"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/qwen3.8-2.4t-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":31},"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":0,"losses":1,"wins":61},"thinkingmachines/inkling":{"draws":1,"losses":0,"wins":33},"thinkingmachines/inkling-small":{"draws":1,"losses":0,"wins":47},"x-ai/grok-4.5":{"draws":0,"losses":1,"wins":39},"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":26},"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":36,"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":16,"wins":45},"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":91},"google/gemini-3.6-flash":{"draws":54,"losses":94,"wins":62},"google/gemini-3.8-flash":{"draws":13,"losses":28,"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":7,"losses":7,"wins":6},"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":2,"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":54,"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":35},"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":31,"wins":88},"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":18,"losses":28,"wins":14},"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":10,"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":3,"wins":47},"thinkingmachines/inkling-small":{"draws":24,"losses":12,"wins":18},"x-ai/grok-4.5":{"draws":36,"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":10,"losses":23,"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":1,"wins":7},"claude-fable-5":{"draws":1,"losses":2,"wins":3},"claude-fable-5-1":{"draws":0,"losses":11,"wins":5},"claude-opus-4-5":{"draws":6,"losses":11,"wins":57},"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":20},"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":18},"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":9,"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":4},"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":0,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":3,"losses":0,"wins":7},"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":33},"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":34},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":8},"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":2,"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":3,"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":23},"claude-fable-5-1":{"draws":7,"losses":9,"wins":16},"claude-opus-4-5":{"draws":4,"losses":8,"wins":102},"claude-opus-4-8":{"draws":5,"losses":23,"wins":62},"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":10},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":2,"wins":11},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":1,"wins":7},"google/gemini-3.1-flash-lite":{"draws":1,"losses":2,"wins":37},"google/gemini-3.5-flash":{"draws":4,"losses":2,"wins":28},"google/gemini-3.5-flash-lite":{"draws":5,"losses":5,"wins":66},"google/gemini-3.6-flash":{"draws":7,"losses":12,"wins":61},"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":23},"gpt-5.6-sol":{"draws":9,"losses":5,"wins":26},"gpt-5.6-terra":{"draws":2,"losses":0,"wins":20},"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":3},"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":18},"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":18},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":1,"wins":11},"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":75},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":16},"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":57},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":20},"x-ai/grok-4.7":{"draws":0,"losses":0,"wins":4},"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":4,"wins":40},"z-ai/glm-5.3":{"draws":4,"losses":2,"wins":18},"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":9},"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":2},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":6},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":0,"wins":10},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":6},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":12},"google/gemini-3.6-flash":{"draws":0,"losses":0,"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":4},"gpt-5.5":{"draws":0,"losses":0,"wins":2},"gpt-5.6-luna":{"draws":0,"losses":0,"wins":4},"gpt-5.6-sol":{"draws":1,"losses":0,"wins":9},"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":12},"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":6},"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":10},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":8},"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":33},"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":6},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":4},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":14},"x-ai/grok-4.6":{"draws":0,"losses":0,"wins":6},"x-ai/grok-4.7":{"draws":1,"losses":4,"wins":19},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":0,"losses":0,"wins":18},"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":30},"claude-opus-4-8":{"draws":3,"losses":6,"wins":3},"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":18},"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":17},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":3},"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":21},"gpt-6-astra":{"draws":1,"losses":46,"wins":7},"gpt-6-luna":{"draws":1,"losses":0,"wins":1},"gpt-6-sol":{"draws":2,"losses":7,"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":2,"wins":30},"meta/muse-glimmer-30b":{"draws":9,"losses":3,"wins":14},"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":14,"losses":14,"wins":14},"qwen/qwen3.8-27b":{"draws":9,"losses":5,"wins":12},"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":3},"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":0,"losses":2,"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":3,"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":8,"wins":3},"claude-opus-5-5":{"draws":0,"losses":5,"wins":1},"claude-sonnet-5":{"draws":21,"losses":17,"wins":8},"cohere/north-mini-code":{"draws":3,"losses":0,"wins":1},"deepseek/deepseek-v4-flash":{"draws":6,"losses":13,"wins":19},"deepseek/deepseek-v4-pro":{"draws":22,"losses":18,"wins":8},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":12,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":7,"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":28,"wins":11},"google/gemini-3.8-flash":{"draws":10,"losses":16,"wins":10},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":2},"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":1,"wins":9},"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":16,"losses":3,"wins":3},"moonshotai/kimi-k2.7-code":{"draws":3,"losses":2,"wins":1},"moonshotai/kimi-k3":{"draws":11,"losses":11,"wins":12},"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":4,"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":10,"losses":25,"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":2,"losses":7,"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":17},"claude-fable-5":{"draws":9,"losses":26,"wins":11},"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":7,"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":16,"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":20,"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":12,"losses":2,"wins":2},"gpt-5.4":{"draws":26,"losses":16,"wins":8},"gpt-5.4-mini":{"draws":1,"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":41,"wins":3},"gpt-6-luna":{"draws":0,"losses":8,"wins":0},"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":9},"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":2,"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":12,"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":0,"wins":0},"stealth/ox-alpha":{"draws":55,"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":3,"wins":1},"x-ai/grok-build-0.1":{"draws":0,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":8,"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},"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":16,"losses":4,"wins":24},"deepseek/deepseek-v4-pro":{"draws":14,"losses":14,"wins":24},"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":37},"google/gemini-3.6-flash":{"draws":22,"losses":33,"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":5,"wins":15},"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":0,"wins":4},"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":25,"wins":16},"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":13,"losses":4,"wins":15},"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":1,"wins":6},"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":1,"losses":1,"wins":6},"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":12,"wins":21},"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":19},"qwen/qwen3.8-max-0902":{"draws":5,"losses":1,"wins":0},"stealth/ox-alpha":{"draws":39,"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":4,"wins":2},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":10,"losses":3,"wins":5},"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":27,"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":0,"losses":0,"wins":2},"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":11,"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":19},"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":2},"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":3},"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":3},"gpt-6-astra":{"draws":1,"losses":8,"wins":1},"gpt-6-luna":{"draws":5,"losses":2,"wins":5},"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":3},"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":6},"openai/gpt-oss-120b":{"draws":1,"losses":3,"wins":10},"qwen/qwen3.7-max":{"draws":2,"losses":0,"wins":0},"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":0,"wins":5},"qwen/qwen3.8-max-0902":{"draws":5,"losses":3,"wins":10},"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":0,"losses":2,"wins":0},"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":0,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":1,"losses":2,"wins":11},"z-ai/glm-5.3":{"draws":4,"losses":2,"wins":2},"z-ai/glm-5.3-flash":{"draws":1,"losses":1,"wins":4},"z-ai/glm-5.3-flashx":{"draws":2,"losses":2,"wins":4}},"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":6,"losses":6,"wins":0},"cohere/north-mini-code":{"draws":7,"losses":2,"wins":11},"deepseek/deepseek-v4-flash":{"draws":11,"losses":15,"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":15,"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":5,"wins":1},"gpt-6-sol":{"draws":1,"losses":5,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":6,"losses":2,"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":2,"losses":4,"wins":0},"minimax/minimax-m3":{"draws":4,"losses":4,"wins":6},"mistralai/mistral-medium-3-5":{"draws":2,"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":7,"wins":1},"qwen/qwen3.7-plus":{"draws":2,"losses":4,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":4,"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":11,"losses":12,"wins":7},"z-ai/glm-5.3":{"draws":1,"losses":6,"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":57,"wins":10},"claude-opus-4-5":{"draws":12,"losses":9,"wins":35},"claude-opus-4-8":{"draws":11,"losses":6,"wins":5},"claude-opus-5":{"draws":6,"losses":22,"wins":4},"claude-opus-5-5":{"draws":0,"losses":6,"wins":2},"claude-sonnet-5":{"draws":12,"losses":7,"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":7,"wins":26},"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":2,"wins":21},"google/gemini-3.5-flash-lite":{"draws":18,"losses":8,"wins":48},"google/gemini-3.6-flash":{"draws":11,"losses":19,"wins":38},"google/gemini-3.8-flash":{"draws":8,"losses":17,"wins":25},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":2},"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":7,"wins":18},"gpt-5.6-sol":{"draws":8,"losses":27,"wins":21},"gpt-5.6-terra":{"draws":19,"losses":13,"wins":16},"gpt-6-astra":{"draws":10,"losses":47,"wins":3},"gpt-6-luna":{"draws":2,"losses":0,"wins":6},"gpt-6-sol":{"draws":2,"losses":3,"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":1,"wins":26},"meta/muse-glimmer-30b":{"draws":3,"losses":4,"wins":21},"meta/muse-spark-1.2":{"draws":6,"losses":13,"wins":17},"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":3,"losses":11,"wins":34},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":21},"poolside/laguna-s-2.1":{"draws":8,"losses":0,"wins":20},"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":15,"wins":24},"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":43,"losses":57,"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":8,"losses":27,"wins":17},"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":12},"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":12},"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":17,"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":26,"losses":25,"wins":25},"claude-fable-5":{"draws":11,"losses":36,"wins":11},"claude-fable-5-1":{"draws":6,"losses":60,"wins":0},"claude-opus-4-5":{"draws":42,"losses":66,"wins":50},"claude-opus-4-8":{"draws":3,"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":42,"losses":71,"wins":45},"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":19},"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":25},"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":40,"wins":6},"google/gemma-4-31b-it":{"draws":4,"losses":4,"wins":4},"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":8},"gpt-5.4-nano":{"draws":3,"losses":8,"wins":15},"gpt-5.5":{"draws":10,"losses":14,"wins":4},"gpt-5.6-luna":{"draws":46,"losses":53,"wins":61},"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":4,"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":31},"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":32,"wins":13},"minimax/minimax-m3":{"draws":4,"losses":6,"wins":6},"mistralai/mistral-medium-3-5":{"draws":14,"losses":10,"wins":30},"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":122,"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":23,"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":117,"wins":72},"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":34,"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":32,"wins":46},"z-ai/glm-5.3":{"draws":14,"losses":48,"wins":6},"z-ai/glm-5.3-flash":{"draws":16,"losses":34,"wins":10},"z-ai/glm-5.3-flashx":{"draws":3,"losses":8,"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":17,"losses":66,"wins":15},"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":4},"deepseek/deepseek-v4-flash":{"draws":10,"losses":3,"wins":53},"deepseek/deepseek-v4-pro":{"draws":15,"losses":20,"wins":33},"deepseek/deepseek-v4-pro-0813":{"draws":24,"losses":12,"wins":38},"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":182},"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":18},"gpt-5.4":{"draws":22,"losses":62,"wins":54},"gpt-5.4-mini":{"draws":3,"losses":2,"wins":13},"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":44,"wins":10},"gpt-6-luna":{"draws":9,"losses":1,"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":17},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"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":27},"o3":{"draws":32,"losses":39,"wins":131},"openai/gpt-oss-120b":{"draws":13,"losses":3,"wins":26},"poolside/laguna-s-2.1":{"draws":30,"losses":3,"wins":49},"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":22,"wins":48},"qwen/qwen3.8-27b":{"draws":14,"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":3,"wins":6},"stealth/ox-alpha":{"draws":40,"losses":63,"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":13,"losses":40,"wins":73},"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":2,"losses":5,"wins":9},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":15,"losses":15,"wins":48},"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":7}},"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":5,"losses":9,"wins":26},"claude-opus-4-8":{"draws":1,"losses":3,"wins":2},"claude-opus-5":{"draws":2,"losses":39,"wins":11},"claude-opus-5-5":{"draws":1,"losses":3,"wins":0},"claude-sonnet-5":{"draws":6,"losses":12,"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":55},"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":6},"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":26},"gpt-5.6-terra":{"draws":10,"losses":11,"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":0,"wins":12},"inclusionai/ling-3.0-flash":{"draws":0,"losses":1,"wins":9},"meituan/longcat-2.0":{"draws":8,"losses":2,"wins":21},"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":5,"wins":4},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":16,"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":46,"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":6,"losses":19,"wins":15},"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":9},"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":27,"losses":11,"wins":16},"claude-opus-4-8":{"draws":13,"losses":31,"wins":8},"claude-opus-5":{"draws":7,"losses":76,"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":5,"wins":6},"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":16,"losses":7,"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":8,"losses":1,"wins":13},"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":3,"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},"moonshotai/kimi-k2.7-code":{"draws":5,"losses":2,"wins":5},"moonshotai/kimi-k3":{"draws":5,"losses":7,"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":4,"losses":2,"wins":6},"poolside/laguna-s-2.1":{"draws":9,"losses":13,"wins":6},"qwen/qwen3.7-max":{"draws":12,"losses":2,"wins":8},"qwen/qwen3.7-plus":{"draws":6,"losses":1,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":1,"losses":2,"wins":3},"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":13,"losses":22,"wins":7},"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":0,"losses":12,"wins":2},"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":12},"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":23,"losses":23,"wins":88},"google/gemini-3.8-flash":{"draws":3,"losses":14,"wins":29},"google/gemma-4-31b-it":{"draws":2,"losses":2,"wins":4},"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":10},"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":1},"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":31},"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":3,"losses":10,"wins":23},"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":0,"losses":0,"wins":4},"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":0,"wins":6},"o3":{"draws":0,"losses":9,"wins":79},"openai/gpt-oss-120b":{"draws":6,"losses":0,"wins":12},"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":77},"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":6,"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":4}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":2,"wins":8},"claude-fable-5":{"draws":3,"losses":4,"wins":3},"claude-fable-5-1":{"draws":0,"losses":11,"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":9},"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":7,"losses":3,"wins":6},"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":2,"wins":12},"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":16,"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":5,"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":2},"nex-agi/nex-n2-pro":{"draws":2,"losses":0,"wins":26},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":1,"wins":24},"o3":{"draws":1,"losses":3,"wins":38},"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":3,"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":12,"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":2,"losses":1,"wins":3},"xiaomi/mimo-v2.5":{"draws":11,"losses":2,"wins":19},"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":11,"losses":15,"wins":16},"claude-fable-5-1":{"draws":3,"losses":39,"wins":4},"claude-opus-4-5":{"draws":27,"losses":17,"wins":30},"claude-opus-4-8":{"draws":2,"losses":4,"wins":4},"claude-opus-5":{"draws":3,"losses":20,"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":10,"wins":17},"google/gemini-3.5-flash-lite":{"draws":70,"losses":23,"wins":81},"google/gemini-3.6-flash":{"draws":43,"losses":47,"wins":56},"google/gemini-3.8-flash":{"draws":12,"losses":18,"wins":24},"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":10},"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":8,"losses":38,"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":21,"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":40},"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":8},"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":100},"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":97},"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":6},"gpt-5.4":{"draws":7,"losses":25,"wins":62},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":12},"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":74},"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":45,"wins":8},"gpt-6-luna":{"draws":0,"losses":1,"wins":9},"gpt-6-sol":{"draws":1,"losses":3,"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":45},"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":35},"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":31},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":5},"x-ai/grok-build-0.1":{"draws":1,"losses":2,"wins":3},"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":35},"z-ai/glm-5.3":{"draws":6,"losses":17,"wins":33},"z-ai/glm-5.3-flash":{"draws":6,"losses":12,"wins":30},"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":21,"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":14,"wins":0},"claude-opus-5-5":{"draws":0,"losses":8,"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},"google/gemini-3.1-flash-lite":{"draws":2,"losses":2,"wins":16},"google/gemini-3.5-flash":{"draws":15,"losses":10,"wins":27},"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":4},"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":5,"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":9,"losses":3,"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":10},"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":15},"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":41,"losses":50,"wins":51},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":10},"tencent/hy3-preview":{"draws":4,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":11,"losses":14,"wins":19},"thinkingmachines/inkling":{"draws":10,"losses":7,"wins":27},"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":26,"wins":6},"x-ai/grok-4.7":{"draws":0,"losses":2,"wins":2},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":0},"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":2,"wins":2},"z-ai/glm-5.2":{"draws":28,"losses":14,"wins":28},"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":18},"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":44},"claude-opus-4-8":{"draws":1,"losses":0,"wins":15},"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":2},"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":51},"google/gemini-3.6-flash":{"draws":3,"losses":1,"wins":54},"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":2},"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":12},"gpt-5.5":{"draws":0,"losses":0,"wins":6},"gpt-5.6-luna":{"draws":5,"losses":0,"wins":29},"gpt-5.6-sol":{"draws":2,"losses":4,"wins":50},"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":20},"meta/muse-spark-1.2":{"draws":0,"losses":0,"wins":30},"meta/muse-spark-1.3":{"draws":2,"losses":1,"wins":39},"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":37},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":20},"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":37},"qwen/qwen3.8-max-0902":{"draws":1,"losses":0,"wins":11},"stealth/ox-alpha":{"draws":7,"losses":4,"wins":149},"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":4,"wins":0},"claude-opus-4-5":{"draws":3,"losses":2,"wins":5},"claude-opus-4-8":{"draws":0,"losses":2,"wins":2},"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":0,"wins":3},"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":2,"wins":6},"google/gemini-3.1-flash-lite":{"draws":0,"losses":1,"wins":3},"google/gemini-3.5-flash":{"draws":0,"losses":2,"wins":0},"google/gemini-3.5-flash-lite":{"draws":1,"losses":3,"wins":14},"google/gemini-3.6-flash":{"draws":2,"losses":10,"wins":6},"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":0,"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":0,"losses":0,"wins":2},"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":1,"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":0,"losses":2,"wins":4},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":6},"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":4},"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":1},"qwen/qwen3.8-max":{"draws":0,"losses":0,"wins":2},"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":3,"losses":1,"wins":6},"thinkingmachines/inkling-small":{"draws":2,"losses":0,"wins":8},"x-ai/grok-4.5":{"draws":2,"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":1,"losses":3,"wins":2},"z-ai/glm-5.3-flash":{"draws":1,"losses":3,"wins":2},"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":8},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"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":4},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":8},"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":5},"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":4},"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":4},"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":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":1,"losses":0,"wins":9},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":0,"losses":0,"wins":4},"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":0},"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":10},"stealth/ox-alpha":{"draws":5,"losses":4,"wins":21},"stepfun/step-3.7-flash":{"draws":0,"losses":1,"wins":5},"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":10},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":12},"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":2,"losses":0,"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":4,"losses":2,"wins":0},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"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":7,"wins":11},"claude-fable-5":{"draws":7,"losses":11,"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":28,"wins":5},"google/gemini-3.6-flash":{"draws":30,"losses":36,"wins":4},"google/gemini-3.8-flash":{"draws":12,"losses":18,"wins":0},"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":3,"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":10,"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":8,"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":16,"losses":9,"wins":11},"poolside/laguna-s-2.1":{"draws":14,"losses":12,"wins":2},"qwen/qwen3.7-max":{"draws":2,"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":43,"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":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"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":10,"losses":16,"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":2,"losses":5,"wins":3},"claude-opus-5":{"draws":4,"losses":11,"wins":3},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":20,"losses":16,"wins":8},"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":8},"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":14,"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":20,"wins":4},"gpt-5.6-terra":{"draws":27,"losses":14,"wins":7},"gpt-6-astra":{"draws":4,"losses":28,"wins":0},"gpt-6-luna":{"draws":6,"losses":0,"wins":2},"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":12},"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":20,"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":5},"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":8,"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":14,"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":16,"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":5},"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":1},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.5":{"draws":2,"losses":1,"wins":5},"gpt-5.6-luna":{"draws":0,"losses":9,"wins":17},"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":0,"wins":0},"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":15},"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":10},"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":4},"google/gemini-3.5-flash":{"draws":4,"losses":9,"wins":19},"google/gemini-3.5-flash-lite":{"draws":3,"losses":6,"wins":31},"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":16},"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":23},"gpt-5.6-terra":{"draws":6,"losses":4,"wins":28},"gpt-6-astra":{"draws":5,"losses":36,"wins":5},"gpt-6-luna":{"draws":0,"losses":0,"wins":2},"gpt-6-sol":{"draws":2,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"losses":0,"wins":4},"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":11},"meta/muse-spark-1.3":{"draws":2,"losses":4,"wins":10},"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":8,"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":16,"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":9,"wins":11},"claude-fable-5":{"draws":13,"losses":7,"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":14,"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":4,"wins":2},"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":15,"losses":23,"wins":6},"gpt-6-astra":{"draws":1,"losses":29,"wins":0},"gpt-6-luna":{"draws":3,"losses":1,"wins":0},"gpt-6-sol":{"draws":0,"losses":2,"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":4,"losses":4,"wins":4},"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":21,"wins":2},"qwen/qwen3.8-27b":{"draws":4,"losses":11,"wins":5},"qwen/qwen3.8-flash":{"draws":11,"losses":9,"wins":4},"qwen/qwen3.8-max":{"draws":16,"losses":18,"wins":6},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":35,"losses":62,"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":26,"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":17,"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":7,"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":9,"wins":14},"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":22,"losses":43,"wins":45},"google/gemini-3.8-flash":{"draws":6,"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":2,"wins":3},"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":1,"wins":2},"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":2},"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":25,"losses":27,"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":3,"losses":0,"wins":13},"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":33,"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":21,"losses":19,"wins":14},"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":2,"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":21,"losses":23,"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":5,"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":2,"losses":3,"wins":5},"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":27,"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":25,"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":0},"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":27,"losses":17,"wins":32},"thinkingmachines/inkling-small":{"draws":9,"losses":3,"wins":2},"x-ai/grok-4.5":{"draws":13,"losses":17,"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":57,"losses":11,"wins":24},"xiaomi/mimo-v2.5-pro":{"draws":10,"losses":6,"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":3,"losses":6,"wins":3},"z-ai/glm-5.3-flashx":{"draws":4,"losses":6,"wins":0}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":14,"losses":35,"wins":59},"claude-fable-5":{"draws":7,"losses":84,"wins":19},"claude-fable-5-1":{"draws":0,"losses":103,"wins":5},"claude-opus-4-5":{"draws":29,"losses":162,"wins":79},"claude-opus-4-8":{"draws":0,"losses":51,"wins":13},"claude-opus-5":{"draws":2,"losses":107,"wins":5},"claude-opus-5-5":{"draws":0,"losses":26,"wins":0},"claude-sonnet-5":{"draws":15,"losses":101,"wins":122},"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":10,"wins":5},"google/gemini-3.1-flash-lite":{"draws":4,"losses":3,"wins":39},"google/gemini-3.5-flash":{"draws":14,"losses":71,"wins":33},"google/gemini-3.5-flash-lite":{"draws":70,"losses":153,"wins":325},"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":36,"wins":24},"gpt-5.4":{"draws":19,"losses":144,"wins":47},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":11},"gpt-5.4-nano":{"draws":2,"losses":22,"wins":28},"gpt-5.5":{"draws":4,"losses":36,"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":20,"wins":64},"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":31},"minimax/minimax-m3":{"draws":2,"losses":7,"wins":19},"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":26,"losses":98,"wins":122},"nex-agi/nex-n2-pro":{"draws":3,"losses":3,"wins":18},"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":13},"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":17,"losses":30,"wins":33},"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":33,"losses":151,"wins":154},"stepfun/step-3.7-flash":{"draws":19,"losses":38,"wins":87},"tencent/hy3-preview":{"draws":7,"losses":15,"wins":20},"tencent/hy4-preview":{"draws":12,"losses":57,"wins":49},"thinkingmachines/inkling":{"draws":29,"losses":44,"wins":140},"thinkingmachines/inkling-small":{"draws":30,"losses":39,"wins":56},"x-ai/grok-4.5":{"draws":9,"losses":134,"wins":69},"x-ai/grok-4.6":{"draws":16,"losses":53,"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":12,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":8,"wins":6},"z-ai/glm-5.2":{"draws":18,"losses":49,"wins":75},"z-ai/glm-5.3":{"draws":7,"losses":76,"wins":25},"z-ai/glm-5.3-flash":{"draws":15,"losses":55,"wins":48},"z-ai/glm-5.3-flashx":{"draws":1,"losses":13,"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":3,"losses":14,"wins":9},"claude-opus-5":{"draws":2,"losses":18,"wins":0},"claude-opus-5-5":{"draws":0,"losses":20,"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":7},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":4,"wins":4},"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":31,"losses":21,"wins":22},"google/gemini-3.6-flash":{"draws":25,"losses":31,"wins":10},"google/gemini-3.8-flash":{"draws":3,"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":16,"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":15,"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":12,"wins":9},"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":8},"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":14,"wins":6},"qwen/qwen3.8-27b":{"draws":4,"losses":13,"wins":7},"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":8,"wins":2},"stealth/ox-alpha":{"draws":31,"losses":45,"wins":29},"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":24,"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":21,"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":5,"wins":19},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":12},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":11,"losses":8,"wins":25},"google/gemini-3.5-flash-lite":{"draws":19,"losses":6,"wins":47},"google/gemini-3.6-flash":{"draws":21,"losses":20,"wins":33},"google/gemini-3.8-flash":{"draws":12,"losses":17,"wins":25},"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":4},"gpt-5.4":{"draws":6,"losses":13,"wins":29},"gpt-5.4-mini":{"draws":0,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":1,"losses":1,"wins":12},"gpt-5.5":{"draws":2,"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":7},"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":16},"meta/muse-glimmer-30b":{"draws":7,"losses":4,"wins":13},"meta/muse-spark-1.2":{"draws":13,"losses":4,"wins":15},"meta/muse-spark-1.3":{"draws":12,"losses":12,"wins":24},"minimax/minimax-m3":{"draws":2,"losses":1,"wins":5},"mistralai/mistral-medium-3-5":{"draws":9,"losses":0,"wins":15},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":1,"wins":1},"moonshotai/kimi-k3":{"draws":19,"losses":8,"wins":15},"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":33},"openai/gpt-oss-120b":{"draws":8,"losses":0,"wins":16},"poolside/laguna-s-2.1":{"draws":11,"losses":0,"wins":9},"qwen/qwen3.7-max":{"draws":0,"losses":1,"wins":1},"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":5},"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":3},"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":2,"losses":2,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":1,"wins":4},"z-ai/glm-5.2":{"draws":21,"losses":11,"wins":24},"z-ai/glm-5.3":{"draws":14,"losses":26,"wins":18},"z-ai/glm-5.3-flash":{"draws":8,"losses":13,"wins":29},"z-ai/glm-5.3-flashx":{"draws":2,"losses":1,"wins":5}},"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":13,"wins":16},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":2,"losses":17,"wins":23},"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":6,"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":18,"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":2,"wins":13},"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":5,"wins":21},"poolside/laguna-s-2.1":{"draws":4,"losses":2,"wins":18},"qwen/qwen3.7-max":{"draws":0,"losses":4,"wins":8},"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":58},"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":7,"losses":16,"wins":19},"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":22}},"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":7},"claude-opus-5":{"draws":1,"losses":20,"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":2},"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":15,"losses":13,"wins":16},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":3,"wins":2},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":16,"losses":16,"wins":12},"google/gemini-3.5-flash-lite":{"draws":19,"losses":12,"wins":43},"google/gemini-3.6-flash":{"draws":14,"losses":34,"wins":32},"google/gemini-3.8-flash":{"draws":16,"losses":27,"wins":9},"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":10,"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":5},"gpt-5.6-luna":{"draws":10,"losses":10,"wins":21},"gpt-5.6-sol":{"draws":12,"losses":30,"wins":8},"gpt-5.6-terra":{"draws":20,"losses":9,"wins":13},"gpt-6-astra":{"draws":7,"losses":41,"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":7,"losses":12,"wins":10},"meta/muse-spark-1.3":{"draws":10,"losses":23,"wins":11},"minimax/minimax-m3":{"draws":2,"losses":2,"wins":2},"mistralai/mistral-medium-3-5":{"draws":9,"losses":1,"wins":12},"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":15,"wins":28},"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":1,"losses":3,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":22,"losses":25,"wins":11},"qwen/qwen3.8-27b":{"draws":7,"losses":6,"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":3,"losses":6,"wins":1},"stealth/ox-alpha":{"draws":42,"losses":72,"wins":58},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":14},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":0},"tencent/hy4-preview":{"draws":9,"losses":19,"wins":18},"thinkingmachines/inkling":{"draws":16,"losses":3,"wins":13},"thinkingmachines/inkling-small":{"draws":30,"losses":15,"wins":39},"x-ai/grok-4.5":{"draws":6,"losses":12,"wins":15},"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":15,"wins":14},"z-ai/glm-5.3":{"draws":8,"losses":34,"wins":10},"z-ai/glm-5.3-flash":{"draws":16,"losses":11,"wins":27},"z-ai/glm-5.3-flashx":{"draws":6,"losses":2,"wins":4}},"qwen/qwen3.8-max-0902":{"bytedance-seed/seed-2.0-code":{"draws":2,"losses":0,"wins":2},"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":6},"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":2,"wins":7},"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":5,"losses":4,"wins":5},"google/gemini-3.8-flash":{"draws":3,"losses":0,"wins":1},"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":4},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":7},"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":6,"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":2,"losses":0,"wins":6},"meituan/longcat-2.0":{"draws":2,"losses":2,"wins":8},"meta/muse-glimmer-30b":{"draws":3,"losses":0,"wins":7},"meta/muse-spark-1.2":{"draws":1,"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":2,"losses":0,"wins":4},"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":2},"x-ai/grok-4.5":{"draws":1,"losses":1,"wins":6},"x-ai/grok-4.6":{"draws":1,"losses":3,"wins":6},"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":3,"losses":4,"wins":19}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":17,"wins":68},"claude-fable-5":{"draws":20,"losses":96,"wins":46},"claude-fable-5-1":{"draws":24,"losses":155,"wins":21},"claude-opus-4-5":{"draws":24,"losses":34,"wins":103},"claude-opus-4-8":{"draws":7,"losses":12,"wins":29},"claude-opus-5":{"draws":15,"losses":75,"wins":13},"claude-opus-5-5":{"draws":1,"losses":25,"wins":2},"claude-sonnet-5":{"draws":17,"losses":38,"wins":86},"cohere/north-mini-code":{"draws":0,"losses":5,"wins":11},"deepseek/deepseek-v4-flash":{"draws":8,"losses":10,"wins":91},"deepseek/deepseek-v4-pro":{"draws":17,"losses":27,"wins":62},"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":12},"google/gemini-3.5-flash":{"draws":19,"losses":52,"wins":86},"google/gemini-3.5-flash-lite":{"draws":21,"losses":20,"wins":136},"google/gemini-3.6-flash":{"draws":25,"losses":82,"wins":116},"google/gemini-3.8-flash":{"draws":23,"losses":60,"wins":83},"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":133,"wins":25},"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":8},"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":49},"meta/muse-glimmer-30b":{"draws":5,"losses":2,"wins":61},"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":8,"losses":7,"wins":29},"moonshotai/kimi-k2.7-code":{"draws":1,"losses":1,"wins":2},"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":4,"losses":40,"wins":92},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":61},"poolside/laguna-s-2.1":{"draws":15,"losses":6,"wins":52},"qwen/qwen3.7-max":{"draws":1,"losses":6,"wins":25},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":32,"losses":43,"wins":81},"qwen/qwen3.8-27b":{"draws":10,"losses":20,"wins":53},"qwen/qwen3.8-flash":{"draws":17,"losses":24,"wins":54},"qwen/qwen3.8-max":{"draws":21,"losses":42,"wins":95},"qwen/qwen3.8-max-0902":{"draws":7,"losses":8,"wins":19},"stealth/ox-alpha":{"draws":88,"losses":120,"wins":309},"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":13,"losses":3,"wins":86},"x-ai/grok-4.5":{"draws":9,"losses":53,"wins":44},"x-ai/grok-4.6":{"draws":27,"losses":68,"wins":73},"x-ai/grok-4.7":{"draws":0,"losses":9,"wins":1},"x-ai/grok-build-0.1":{"draws":1,"losses":1,"wins":12},"xiaomi/mimo-v2.5":{"draws":6,"losses":2,"wins":48},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":6,"wins":20},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":6,"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":76,"wins":62},"z-ai/glm-5.3-flash":{"draws":21,"losses":49,"wins":83},"z-ai/glm-5.3-flashx":{"draws":6,"losses":7,"wins":15}},"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":22,"wins":0},"claude-opus-5-5":{"draws":0,"losses":2,"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":24,"wins":2},"gpt-5.4":{"draws":5,"losses":9,"wins":4},"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":2,"losses":2,"wins":8},"meituan/longcat-2.0":{"draws":12,"losses":8,"wins":6},"meta/muse-glimmer-30b":{"draws":0,"losses":6,"wins":0},"meta/muse-spark-1.2":{"draws":0,"losses":9,"wins":1},"meta/muse-spark-1.3":{"draws":0,"losses":12,"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":8,"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":14,"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":6,"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":4},"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":6,"losses":5,"wins":3},"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":3,"wins":3},"inclusionai/ling-3.0-flash":{"draws":4,"losses":4,"wins":10},"meituan/longcat-2.0":{"draws":7,"losses":12,"wins":13},"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":4,"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":11},"x-ai/grok-4.5":{"draws":4,"losses":22,"wins":0},"x-ai/grok-4.6":{"draws":3,"losses":4,"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":2,"wins":0},"z-ai/glm-5.2":{"draws":13,"losses":14,"wins":17},"z-ai/glm-5.3":{"draws":1,"losses":1,"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":2,"losses":52,"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":5,"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":6},"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":34},"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":14},"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":9,"losses":30,"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":15,"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":4,"losses":1,"wins":3},"o3":{"draws":10,"losses":15,"wins":23},"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":44,"losses":35,"wins":89},"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":31},"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":32,"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":19,"wins":2},"claude-opus-5":{"draws":1,"losses":33,"wins":2},"claude-opus-5-5":{"draws":0,"losses":14,"wins":0},"claude-sonnet-5":{"draws":31,"losses":68,"wins":15},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":5},"deepseek/deepseek-v4-flash":{"draws":27,"losses":21,"wins":12},"deepseek/deepseek-v4-pro":{"draws":22,"losses":22,"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":68,"losses":131,"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":44,"wins":21},"gpt-5.6-sol":{"draws":22,"losses":69,"wins":9},"gpt-5.6-terra":{"draws":21,"losses":29,"wins":8},"gpt-6-astra":{"draws":3,"losses":33,"wins":0},"gpt-6-luna":{"draws":2,"losses":7,"wins":1},"gpt-6-sol":{"draws":1,"losses":10,"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":10},"meituan/longcat-2.0":{"draws":21,"losses":26,"wins":47},"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":4,"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":6,"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":20,"wins":5},"qwen/qwen3.8-flash":{"draws":13,"losses":17,"wins":8},"qwen/qwen3.8-max":{"draws":16,"losses":21,"wins":15},"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":14,"losses":16,"wins":4},"x-ai/grok-4.7":{"draws":2,"losses":0,"wins":0},"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":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":0},"z-ai/glm-5.2":{"draws":27,"losses":27,"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":19,"wins":12},"claude-opus-4-8":{"draws":8,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":29,"wins":1},"claude-opus-5-5":{"draws":2,"losses":4,"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":12,"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":49},"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":8},"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":14,"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":3},"o3":{"draws":19,"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":20,"losses":20,"wins":8},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":7},"qwen/qwen3.8-flash":{"draws":15,"losses":7,"wins":8},"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":48,"losses":88,"wins":26},"stepfun/step-3.7-flash":{"draws":4,"losses":3,"wins":7},"tencent/hy3-preview":{"draws":3,"losses":1,"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":2,"wins":0},"x-ai/grok-build-0.1":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.5":{"draws":5,"losses":2,"wins":5},"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":27,"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":61},"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":4},"deepseek/deepseek-v4-flash":{"draws":7,"losses":10,"wins":27},"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":14},"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":24,"losses":78,"wins":102},"google/gemini-3.8-flash":{"draws":6,"losses":15,"wins":29},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":6,"losses":4,"wins":14},"gpt-5.4":{"draws":24,"losses":34,"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":25,"losses":7,"wins":52},"meta/muse-glimmer-30b":{"draws":8,"losses":6,"wins":22},"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":9},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"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":32,"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":45},"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":10,"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":23},"claude-fable-5-1":{"draws":4,"losses":49,"wins":13},"claude-opus-4-5":{"draws":12,"losses":7,"wins":29},"claude-opus-4-8":{"draws":1,"losses":11,"wins":8},"claude-opus-5":{"draws":2,"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":10,"losses":14,"wins":26},"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":15,"wins":21},"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":23},"gpt-5.6-sol":{"draws":8,"losses":19,"wins":33},"gpt-5.6-terra":{"draws":9,"losses":5,"wins":38},"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":5,"losses":7,"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":69},"stepfun/step-3.7-flash":{"draws":1,"losses":2,"wins":5},"tencent/hy3-preview":{"draws":0,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":16,"losses":12,"wins":20},"thinkingmachines/inkling":{"draws":9,"losses":4,"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":10},"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":8,"wins":33},"z-ai/glm-5.3":{"draws":11,"losses":22,"wins":19},"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":2},"deepseek/deepseek-v4-pro":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":2,"wins":4},"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":3},"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/qwen3.8-2.4t-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":2,"wins":4},"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":1,"losses":0,"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":4,"losses":2,"wins":0},"claude-fable-5":{"draws":4,"losses":6,"wins":0},"claude-fable-5-1":{"draws":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":31,"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":0,"losses":4,"wins":0},"inception/mercury-2.5-preview":{"draws":2,"losses":0,"wins":0},"inclusionai/ling-3.0-flash":{"draws":14,"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":2,"losses":0,"wins":0},"moonshotai/kimi-k2.7-code":{"draws":8,"losses":2,"wins":0},"moonshotai/kimi-k3":{"draws":2,"losses":2,"wins":0},"nex-agi/nex-n2-pro":{"draws":12,"losses":0,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":36,"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":14,"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":14,"losses":12,"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":27,"losses":23,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":8,"wins":4},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":2,"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":2,"losses":2,"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":17,"wins":3},"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":14,"losses":18,"wins":6},"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":1,"wins":4},"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":31,"wins":6},"gpt-5.6-terra":{"draws":25,"losses":24,"wins":3},"gpt-6-astra":{"draws":4,"losses":32,"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":7,"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":11,"losses":26,"wins":13},"openai/gpt-oss-120b":{"draws":17,"losses":7,"wins":26},"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":44,"losses":70,"wins":32},"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":10},"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":14,"wins":9},"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":9,"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":22},"claude-fable-5":{"draws":5,"losses":5,"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":1,"losses":1,"wins":4},"claude-opus-5":{"draws":6,"losses":6,"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":27},"deepseek/deepseek-v4-pro-0813":{"draws":4,"losses":0,"wins":26},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":1,"wins":5},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":4},"google/gemini-3.5-flash":{"draws":2,"losses":0,"wins":30},"google/gemini-3.5-flash-lite":{"draws":5,"losses":0,"wins":53},"google/gemini-3.6-flash":{"draws":3,"losses":3,"wins":60},"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":13},"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":6},"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":35},"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":16},"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":3},"stealth/ox-alpha":{"draws":20,"losses":11,"wins":95},"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":0,"wins":20},"thinkingmachines/inkling-small":{"draws":3,"losses":0,"wins":19},"x-ai/grok-4.5":{"draws":10,"losses":3,"wins":23},"x-ai/grok-4.6":{"draws":6,"losses":6,"wins":36},"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":6},"z-ai/glm-5.2":{"draws":6,"losses":0,"wins":34},"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":18,"wins":21},"claude-fable-5-1":{"draws":7,"losses":35,"wins":8},"claude-opus-4-5":{"draws":10,"losses":7,"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":2,"losses":10,"wins":0},"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":3},"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":38},"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":2},"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":0,"wins":6},"gpt-6-sol":{"draws":2,"losses":10,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"losses":0,"wins":0},"inception/mercury-2.5-preview":{"draws":10,"losses":7,"wins":13},"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":14,"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":9,"losses":22,"wins":17},"openai/gpt-oss-120b":{"draws":10,"losses":3,"wins":21},"poolside/laguna-s-2.1":{"draws":13,"losses":1,"wins":20},"qwen/qwen3.7-max":{"draws":0,"losses":0,"wins":2},"qwen/qwen3.7-plus":{"draws":0,"losses":0,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":7,"losses":16,"wins":23},"qwen/qwen3.8-27b":{"draws":7,"losses":12,"wins":13},"qwen/qwen3.8-flash":{"draws":8,"losses":9,"wins":9},"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":6,"losses":8,"wins":16},"x-ai/grok-4.6":{"draws":5,"losses":20,"wins":21},"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":6},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":0,"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":0,"wins":3}},"z-ai/glm-5.3-flashx":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":1,"wins":6},"claude-fable-5":{"draws":1,"losses":0,"wins":5},"claude-fable-5-1":{"draws":3,"losses":5,"wins":0},"claude-opus-4-5":{"draws":0,"losses":0,"wins":4},"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":2,"losses":0,"wins":8},"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":5,"losses":0,"wins":9},"google/gemini-3.8-flash":{"draws":0,"losses":1,"wins":3},"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":0,"wins":4},"gpt-5.4-mini":{"draws":0,"losses":2,"wins":4},"gpt-5.4-nano":{"draws":0,"losses":1,"wins":7},"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":5},"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":4},"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":2,"losses":0,"wins":2},"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":5,"wins":17},"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":0,"losses":2,"wins":4},"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":3,"losses":1,"wins":4},"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":4,"losses":8,"wins":10},"z-ai/glm-5.2":{"draws":3,"losses":0,"wins":7},"z-ai/glm-5.3":{"draws":1,"losses":6,"wins":1},"z-ai/glm-5.3-flash":{"draws":3,"losses":3,"wins":2},"z-ai/glm-5.3-flashx":{"draws":8,"losses":3,"wins":13}}},"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":18},"claude-opus-4-8":{"draws":4,"losses":2,"wins":6},"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":0,"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":13},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":0,"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":14,"wins":8},"gpt-6-luna":{"draws":0,"losses":1,"wins":1},"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":9,"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":6},"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":4,"losses":15,"wins":13},"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":0,"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":7},"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":28,"losses":47,"wins":35},"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":18,"wins":9},"thinkingmachines/inkling":{"draws":8,"losses":9,"wins":21},"thinkingmachines/inkling-small":{"draws":15,"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":6,"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":17,"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":44,"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":1,"losses":6,"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":7,"losses":11,"wins":26},"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":11,"losses":14,"wins":31},"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":3},"gpt-5.4-nano":{"draws":1,"losses":3,"wins":6},"gpt-5.5":{"draws":0,"losses":3,"wins":7},"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":5,"losses":5,"wins":6},"meta/muse-spark-1.2":{"draws":5,"losses":9,"wins":14},"meta/muse-spark-1.3":{"draws":6,"losses":15,"wins":23},"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":1,"losses":4,"wins":35},"openai/gpt-oss-120b":{"draws":12,"losses":5,"wins":15},"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":14},"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":40,"losses":32,"wins":78},"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":29},"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":19,"wins":16},"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":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":2},"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":10,"losses":13,"wins":27},"z-ai/glm-5.3-flashx":{"draws":0,"losses":3,"wins":5}},"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":51},"claude-opus-4-8":{"draws":2,"losses":3,"wins":7},"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":5},"google/gemini-3.5-flash":{"draws":5,"losses":4,"wins":39},"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":12},"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":4},"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":41},"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":4},"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":10},"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":18},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":6,"wins":42},"qwen/qwen3.8-27b":{"draws":1,"losses":0,"wins":23},"qwen/qwen3.8-flash":{"draws":1,"losses":2,"wins":27},"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":7},"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":7,"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":2,"losses":58,"wins":0},"claude-opus-4-5":{"draws":15,"losses":13,"wins":26},"claude-opus-4-8":{"draws":10,"losses":11,"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":12,"losses":14,"wins":32},"deepseek/deepseek-v4-pro":{"draws":5,"losses":17,"wins":18},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":17,"wins":18},"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":28,"wins":16},"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":50,"wins":19},"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":19},"meta/muse-spark-1.2":{"draws":19,"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":18,"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":58,"wins":48},"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":38},"thinkingmachines/inkling-small":{"draws":6,"losses":3,"wins":34},"x-ai/grok-4.5":{"draws":30,"losses":41,"wins":29},"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":16},"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":2},"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":2,"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":4,"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":4},"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":5,"wins":4},"google/gemma-4-31b-it":{"draws":13,"losses":0,"wins":17},"gpt-4.1":{"draws":11,"losses":3,"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":5},"nex-agi/nex-n2-pro":{"draws":21,"losses":0,"wins":17},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":14,"losses":6,"wins":10},"o3":{"draws":8,"losses":4,"wins":16},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":2},"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":5,"losses":2,"wins":1},"qwen/qwen3.8-max":{"draws":9,"losses":3,"wins":4},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":1},"stealth/ox-alpha":{"draws":18,"losses":28,"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":7,"wins":5},"thinkingmachines/inkling":{"draws":15,"losses":9,"wins":14},"thinkingmachines/inkling-small":{"draws":6,"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":9,"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":33},"deepseek/deepseek-v4-pro":{"draws":1,"losses":4,"wins":19},"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":64},"google/gemini-3.6-flash":{"draws":6,"losses":13,"wins":59},"google/gemini-3.8-flash":{"draws":7,"losses":6,"wins":27},"google/gemma-4-31b-it":{"draws":5,"losses":6,"wins":13},"gpt-4.1":{"draws":2,"losses":4,"wins":24},"gpt-5":{"draws":8,"losses":4,"wins":54},"gpt-5.4":{"draws":0,"losses":2,"wins":12},"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":15},"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":5,"wins":7},"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":63},"meta/muse-glimmer-30b":{"draws":1,"losses":3,"wins":14},"meta/muse-spark-1.2":{"draws":1,"losses":4,"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":6},"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":69},"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":12},"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":13},"qwen/qwen3.8-max-0902":{"draws":4,"losses":4,"wins":8},"stealth/ox-alpha":{"draws":10,"losses":6,"wins":71},"stepfun/step-3.7-flash":{"draws":5,"losses":1,"wins":20},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":33},"tencent/hy4-preview":{"draws":1,"losses":3,"wins":18},"thinkingmachines/inkling":{"draws":12,"losses":6,"wins":46},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":16},"x-ai/grok-4.5":{"draws":8,"losses":14,"wins":40},"x-ai/grok-4.6":{"draws":3,"losses":5,"wins":13},"x-ai/grok-4.7":{"draws":2,"losses":6,"wins":8},"x-ai/grok-build-0.1":{"draws":6,"losses":3,"wins":11},"xiaomi/mimo-v2.5":{"draws":23,"losses":7,"wins":70},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":0,"wins":26},"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":6},"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":8},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":0,"wins":10},"google/gemini-3.1-flash-lite":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash":{"draws":0,"losses":0,"wins":8},"google/gemini-3.5-flash-lite":{"draws":0,"losses":0,"wins":10},"google/gemini-3.6-flash":{"draws":0,"losses":0,"wins":18},"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":10},"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":4},"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":12},"poolside/laguna-s-2.1":{"draws":0,"losses":0,"wins":10},"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":9},"stealth/ox-alpha":{"draws":1,"losses":3,"wins":32},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":4},"tencent/hy3-preview":{"draws":0,"losses":0,"wins":6},"tencent/hy4-preview":{"draws":0,"losses":1,"wins":5},"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":14},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":23},"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":0,"losses":0,"wins":22},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":3,"wins":18},"z-ai/glm-5.2":{"draws":0,"losses":0,"wins":18},"z-ai/glm-5.3":{"draws":0,"losses":0,"wins":14},"z-ai/glm-5.3-flash":{"draws":1,"losses":0,"wins":9},"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":39,"wins":13},"claude-opus-4-8":{"draws":3,"losses":3,"wins":0},"claude-opus-5":{"draws":4,"losses":12,"wins":4},"claude-opus-5-5":{"draws":1,"losses":0,"wins":1},"claude-sonnet-5":{"draws":19,"losses":29,"wins":16},"deepseek/deepseek-v4-flash":{"draws":22,"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":8,"losses":0,"wins":10},"google/gemini-3.5-flash":{"draws":20,"losses":19,"wins":13},"google/gemini-3.5-flash-lite":{"draws":59,"losses":43,"wins":78},"google/gemini-3.6-flash":{"draws":50,"losses":68,"wins":32},"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":0,"wins":0},"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":8,"wins":1},"gpt-5.6-luna":{"draws":32,"losses":24,"wins":46},"gpt-5.6-sol":{"draws":14,"losses":80,"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":16,"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":47,"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":4},"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":8},"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":40,"losses":84,"wins":38},"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":26,"losses":17,"wins":25},"z-ai/glm-5.3":{"draws":5,"losses":39,"wins":2},"z-ai/glm-5.3-flash":{"draws":13,"losses":25,"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":5},"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":7,"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":6,"wins":0},"gpt-6-luna":{"draws":1,"losses":1,"wins":0},"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":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":20,"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":8,"losses":5,"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":2,"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":65,"wins":0},"claude-opus-4-5":{"draws":42,"losses":48,"wins":22},"claude-opus-4-8":{"draws":23,"losses":34,"wins":3},"claude-opus-5":{"draws":15,"losses":86,"wins":5},"claude-opus-5-5":{"draws":0,"losses":16,"wins":0},"claude-sonnet-5":{"draws":29,"losses":38,"wins":17},"cohere/north-mini-code":{"draws":18,"losses":16,"wins":20},"deepseek/deepseek-v4-flash":{"draws":29,"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":53},"google/gemini-3.5-flash":{"draws":21,"losses":29,"wins":14},"google/gemini-3.5-flash-lite":{"draws":46,"losses":25,"wins":55},"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":38,"wins":5},"gpt-5.4-mini":{"draws":39,"losses":20,"wins":17},"gpt-5.4-nano":{"draws":29,"losses":23,"wins":36},"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":29,"losses":33,"wins":14},"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":23,"wins":27},"meituan/longcat-2.0":{"draws":32,"losses":22,"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":38,"wins":12},"minimax/minimax-m3":{"draws":24,"losses":26,"wins":24},"mistralai/mistral-medium-3-5":{"draws":13,"losses":7,"wins":18},"moonshotai/kimi-k2.7-code":{"draws":7,"losses":10,"wins":9},"moonshotai/kimi-k3":{"draws":28,"losses":36,"wins":18},"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":42,"losses":20,"wins":30},"qwen/qwen3.7-max":{"draws":22,"losses":16,"wins":14},"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":9,"losses":17,"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":17,"wins":1},"stealth/ox-alpha":{"draws":72,"losses":95,"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":33},"thinkingmachines/inkling-small":{"draws":38,"losses":7,"wins":35},"x-ai/grok-4.5":{"draws":14,"losses":52,"wins":10},"x-ai/grok-4.6":{"draws":29,"losses":47,"wins":6},"x-ai/grok-4.7":{"draws":0,"losses":12,"wins":0},"x-ai/grok-build-0.1":{"draws":18,"losses":9,"wins":13},"xiaomi/mimo-v2.5":{"draws":80,"losses":76,"wins":50},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":20,"wins":13},"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":68,"wins":32},"z-ai/glm-5.3":{"draws":16,"losses":31,"wins":1},"z-ai/glm-5.3-flash":{"draws":15,"losses":34,"wins":13},"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":8,"losses":23,"wins":19},"claude-fable-5-1":{"draws":5,"losses":49,"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":12,"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":13,"losses":14,"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":30,"wins":38},"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":18},"gpt-5.6-sol":{"draws":4,"losses":28,"wins":14},"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":18,"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":32},"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":4,"losses":0,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":21,"wins":12},"qwen/qwen3.8-27b":{"draws":1,"losses":8,"wins":13},"qwen/qwen3.8-flash":{"draws":6,"losses":13,"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":41,"losses":48,"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":9,"losses":6,"wins":17},"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":13},"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":30},"z-ai/glm-5.3":{"draws":7,"losses":31,"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":17,"losses":16,"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":10,"wins":16},"claude-opus-4-8":{"draws":2,"losses":4,"wins":10},"claude-opus-5":{"draws":3,"losses":12,"wins":3},"claude-opus-5-5":{"draws":0,"losses":4,"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":19,"wins":14},"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":2},"gpt-6-sol":{"draws":2,"losses":6,"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":12,"wins":16},"meta/muse-spark-1.3":{"draws":10,"losses":22,"wins":10},"minimax/minimax-m3":{"draws":0,"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":0,"wins":4},"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":8,"wins":15},"poolside/laguna-s-2.1":{"draws":14,"losses":11,"wins":17},"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":22,"losses":14,"wins":10},"qwen/qwen3.8-max-0902":{"draws":2,"losses":1,"wins":3},"stealth/ox-alpha":{"draws":45,"losses":70,"wins":43},"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":11,"losses":21,"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":4,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":2,"losses":6,"wins":14},"xiaomi/mimo-v2.5-pro":{"draws":4,"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":2,"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":6,"wins":5},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"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},"gpt-4.1":{"draws":0,"losses":2,"wins":4},"gpt-5":{"draws":3,"losses":2,"wins":3},"gpt-5.4":{"draws":7,"losses":9,"wins":2},"gpt-5.4-mini":{"draws":5,"losses":0,"wins":1},"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":1,"wins":4},"gpt-6-sol":{"draws":5,"losses":8,"wins":1},"inception/mercury-2.5-preview":{"draws":2,"losses":2,"wins":0},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":3},"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":1,"wins":6},"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":2,"losses":5,"wins":5},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":7,"losses":2,"wins":5},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":6},"stealth/ox-alpha":{"draws":9,"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":7,"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":8,"losses":1,"wins":11},"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":3,"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":5,"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":10,"wins":0},"claude-opus-4-5":{"draws":15,"losses":39,"wins":2},"claude-opus-4-8":{"draws":12,"losses":27,"wins":3},"claude-opus-5":{"draws":7,"losses":20,"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":25,"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":1,"losses":12,"wins":1},"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":8,"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":6,"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":6,"wins":1},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":8},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":8,"wins":18},"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":13,"wins":9},"qwen/qwen3.7-plus":{"draws":6,"losses":12,"wins":10},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"losses":4,"wins":0},"qwen/qwen3.8-27b":{"draws":4,"losses":8,"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":14,"wins":4},"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":5,"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":29,"wins":10},"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":4,"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":13},"deepseek/deepseek-v4-pro":{"draws":13,"losses":8,"wins":13},"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":11,"wins":9},"google/gemini-3.5-flash-lite":{"draws":21,"losses":14,"wins":35},"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":2,"losses":2,"wins":4},"gpt-5.6-luna":{"draws":19,"losses":5,"wins":16},"gpt-5.6-sol":{"draws":8,"losses":33,"wins":15},"gpt-5.6-terra":{"draws":9,"losses":16,"wins":17},"gpt-6-astra":{"draws":6,"losses":44,"wins":2},"gpt-6-luna":{"draws":0,"losses":0,"wins":4},"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":6},"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":2,"losses":2,"wins":0},"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":7,"losses":13,"wins":18},"qwen/qwen3.8-max-0902":{"draws":2,"losses":1,"wins":1},"stealth/ox-alpha":{"draws":40,"losses":43,"wins":64},"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":7,"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":27,"losses":31,"wins":20},"claude-fable-5":{"draws":11,"losses":41,"wins":6},"claude-fable-5-1":{"draws":0,"losses":34,"wins":0},"claude-opus-4-5":{"draws":69,"losses":98,"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":16,"losses":10,"wins":2},"deepseek/deepseek-v4-flash":{"draws":41,"losses":44,"wins":19},"deepseek/deepseek-v4-pro":{"draws":27,"losses":35,"wins":22},"deepseek/deepseek-v4-pro-0813":{"draws":29,"losses":25,"wins":14},"deepseek/deepseek-v4.1-flash":{"draws":7,"losses":13,"wins":2},"google/gemini-3.1-flash-lite":{"draws":16,"losses":11,"wins":15},"google/gemini-3.5-flash":{"draws":23,"losses":40,"wins":19},"google/gemini-3.5-flash-lite":{"draws":112,"losses":119,"wins":95},"google/gemini-3.6-flash":{"draws":127,"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":11},"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":61,"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":9,"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":70,"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":31,"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":9,"losses":5,"wins":6},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":13,"losses":10,"wins":11},"o3":{"draws":51,"losses":169,"wins":38},"openai/gpt-oss-120b":{"draws":31,"losses":32,"wins":17},"poolside/laguna-s-2.1":{"draws":61,"losses":54,"wins":25},"qwen/qwen3.7-max":{"draws":10,"losses":4,"wins":6},"qwen/qwen3.7-plus":{"draws":14,"losses":7,"wins":5},"qwen/qwen3.8-2.4t-a95b":{"draws":28,"losses":36,"wins":4},"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":81,"losses":138,"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":43,"losses":87,"wins":10},"x-ai/grok-4.6":{"draws":33,"losses":33,"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":28,"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":36,"wins":22},"claude-fable-5-1":{"draws":2,"losses":59,"wins":9},"claude-opus-4-5":{"draws":32,"losses":40,"wins":78},"claude-opus-4-8":{"draws":18,"losses":18,"wins":32},"claude-opus-5":{"draws":8,"losses":54,"wins":22},"claude-opus-5-5":{"draws":1,"losses":7,"wins":0},"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":15,"wins":56},"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":15,"losses":24,"wins":27},"google/gemini-3.5-flash-lite":{"draws":71,"losses":41,"wins":157},"google/gemini-3.6-flash":{"draws":45,"losses":66,"wins":115},"google/gemini-3.8-flash":{"draws":11,"losses":25,"wins":26},"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":6,"losses":0,"wins":0},"gpt-5":{"draws":10,"losses":7,"wins":19},"gpt-5.4":{"draws":33,"losses":56,"wins":43},"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":59,"wins":48},"gpt-5.6-terra":{"draws":19,"losses":17,"wins":30},"gpt-6-astra":{"draws":9,"losses":61,"wins":4},"gpt-6-luna":{"draws":1,"losses":6,"wins":13},"gpt-6-sol":{"draws":3,"losses":12,"wins":9},"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":3,"losses":5,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":5,"losses":1,"wins":16},"o3":{"draws":25,"losses":40,"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":9,"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":30},"qwen/qwen3.8-max-0902":{"draws":7,"losses":4,"wins":7},"stealth/ox-alpha":{"draws":52,"losses":79,"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":24,"wins":36},"thinkingmachines/inkling":{"draws":32,"losses":22,"wins":68},"thinkingmachines/inkling-small":{"draws":17,"losses":7,"wins":39},"x-ai/grok-4.5":{"draws":37,"losses":52,"wins":75},"x-ai/grok-4.6":{"draws":20,"losses":27,"wins":23},"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":16},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"wins":6},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":5,"wins":4},"z-ai/glm-5.2":{"draws":32,"losses":30,"wins":40},"z-ai/glm-5.3":{"draws":13,"losses":32,"wins":15},"z-ai/glm-5.3-flash":{"draws":6,"losses":28,"wins":22},"z-ai/glm-5.3-flashx":{"draws":3,"losses":7,"wins":2}},"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":6},"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":18,"losses":10,"wins":12},"deepseek/deepseek-v4-pro-0813":{"draws":15,"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":10,"wins":25},"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":1},"gpt-6-sol":{"draws":1,"losses":7,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":1,"losses":0,"wins":5},"inception/mercury-2.5-preview":{"draws":10,"losses":1,"wins":13},"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":20,"losses":9,"wins":19},"nex-agi/nex-n2-pro":{"draws":2,"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":14,"losses":6,"wins":16},"qwen/qwen3.8-max":{"draws":14,"losses":16,"wins":14},"qwen/qwen3.8-max-0902":{"draws":3,"losses":1,"wins":2},"stealth/ox-alpha":{"draws":41,"losses":48,"wins":81},"stepfun/step-3.7-flash":{"draws":4,"losses":0,"wins":6},"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":16,"losses":2,"wins":14},"x-ai/grok-4.5":{"draws":10,"losses":18,"wins":10},"x-ai/grok-4.6":{"draws":17,"losses":20,"wins":15},"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":2,"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":0,"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":25,"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":4,"losses":6,"wins":2},"google/gemini-3.5-flash-lite":{"draws":5,"losses":11,"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":9},"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":8,"wins":5},"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":3},"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":6,"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":12,"losses":13,"wins":3},"z-ai/glm-5.3":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.3-flash":{"draws":0,"losses":7,"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":36,"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":6,"losses":0,"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":18,"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":15,"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":6},"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":12,"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":17},"openai/gpt-oss-120b":{"draws":0,"losses":0,"wins":2},"poolside/laguna-s-2.1":{"draws":14,"losses":16,"wins":8},"qwen/qwen3.7-max":{"draws":10,"losses":7,"wins":15},"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":10,"losses":2,"wins":8},"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":6},"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":7,"wins":13},"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":20,"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":26},"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":0,"losses":0,"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":49,"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":8,"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":30,"wins":9},"gpt-6-luna":{"draws":1,"losses":1,"wins":2},"gpt-6-sol":{"draws":1,"losses":11,"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":0,"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":20,"wins":14},"qwen/qwen3.8-max-0902":{"draws":4,"losses":6,"wins":8},"stealth/ox-alpha":{"draws":48,"losses":40,"wins":54},"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":13,"wins":15},"thinkingmachines/inkling":{"draws":11,"losses":13,"wins":26},"thinkingmachines/inkling-small":{"draws":31,"losses":4,"wins":22},"x-ai/grok-4.5":{"draws":23,"losses":28,"wins":27},"x-ai/grok-4.6":{"draws":21,"losses":11,"wins":14},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":3},"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":9,"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":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":4,"losses":5,"wins":5},"cohere/north-mini-code":{"draws":6,"losses":1,"wins":15},"deepseek/deepseek-v4-flash":{"draws":14,"losses":4,"wins":20},"deepseek/deepseek-v4-pro":{"draws":2,"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":7},"google/gemini-3.5-flash-lite":{"draws":17,"losses":6,"wins":29},"google/gemini-3.6-flash":{"draws":10,"losses":23,"wins":14},"google/gemini-3.8-flash":{"draws":4,"losses":9,"wins":7},"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":0,"losses":0,"wins":2},"gpt-5.6-sol":{"draws":2,"losses":13,"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":0},"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":21,"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":19,"losses":8,"wins":19},"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":2,"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":6,"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":37},"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":12},"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":45},"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":2,"wins":0},"claude-sonnet-5":{"draws":1,"losses":7,"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":1,"losses":10,"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":8,"wins":5},"gpt-5.4-mini":{"draws":8,"losses":21,"wins":33},"gpt-5.4-nano":{"draws":11,"losses":31,"wins":38},"gpt-5.5":{"draws":20,"losses":33,"wins":23},"gpt-5.6-luna":{"draws":6,"losses":5,"wins":15},"gpt-5.6-sol":{"draws":0,"losses":18,"wins":2},"gpt-5.6-terra":{"draws":3,"losses":8,"wins":9},"gpt-6-astra":{"draws":1,"losses":23,"wins":0},"gpt-6-luna":{"draws":10,"losses":0,"wins":8},"gpt-6-sol":{"draws":0,"losses":8,"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":4},"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":17},"qwen/qwen3.8-2.4t-a95b":{"draws":6,"losses":18,"wins":2},"qwen/qwen3.8-27b":{"draws":2,"losses":19,"wins":3},"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":43,"wins":12},"stepfun/step-3.7-flash":{"draws":14,"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":11,"losses":22,"wins":25},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":22,"losses":41,"wins":41},"z-ai/glm-5.3":{"draws":3,"losses":20,"wins":3},"z-ai/glm-5.3-flash":{"draws":1,"losses":8,"wins":1},"z-ai/glm-5.3-flashx":{"draws":3,"losses":10,"wins":1}},"gpt-5.5":{"bytedance-seed/seed-2.0-code":{"draws":8,"losses":4,"wins":2},"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":60,"wins":16},"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":5},"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":4},"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":7},"gpt-5.6-sol":{"draws":5,"losses":3,"wins":4},"gpt-5.6-terra":{"draws":3,"losses":1,"wins":0},"gpt-6-astra":{"draws":1,"losses":7,"wins":0},"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":5,"wins":3},"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":14},"qwen/qwen3.8-2.4t-a95b":{"draws":4,"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":6,"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":10},"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":3,"losses":10,"wins":15},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":3},"z-ai/glm-5.2":{"draws":30,"losses":15,"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":20,"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":15,"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":56,"losses":43,"wins":77},"google/gemini-3.6-flash":{"draws":45,"losses":72,"wins":39},"google/gemini-3.8-flash":{"draws":16,"losses":27,"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":7,"wins":2},"gpt-5.4":{"draws":33,"losses":54,"wins":15},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":7,"losses":4,"wins":3},"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":66,"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":31,"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":27,"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":36,"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":6,"wins":7},"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":30},"thinkingmachines/inkling-small":{"draws":24,"losses":12,"wins":24},"x-ai/grok-4.5":{"draws":16,"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":17},"claude-fable-5-1":{"draws":8,"losses":48,"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":13,"losses":18,"wins":72},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":10},"deepseek/deepseek-v4-flash":{"draws":5,"losses":2,"wins":29},"deepseek/deepseek-v4-pro":{"draws":2,"losses":10,"wins":24},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":9,"wins":24},"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":10,"wins":23},"google/gemini-3.5-flash-lite":{"draws":17,"losses":18,"wins":101},"google/gemini-3.6-flash":{"draws":20,"losses":45,"wins":67},"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":20},"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":17},"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":18},"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":85},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":8},"tencent/hy3-preview":{"draws":3,"losses":2,"wins":3},"tencent/hy4-preview":{"draws":3,"losses":11,"wins":26},"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":47},"z-ai/glm-5.3":{"draws":13,"losses":16,"wins":19},"z-ai/glm-5.3-flash":{"draws":13,"losses":19,"wins":20},"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":9,"losses":34,"wins":9},"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":25,"losses":10,"wins":17},"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":10},"google/gemini-3.5-flash":{"draws":12,"losses":13,"wins":23},"google/gemini-3.5-flash-lite":{"draws":23,"losses":16,"wins":39},"google/gemini-3.6-flash":{"draws":19,"losses":39,"wins":22},"google/gemini-3.8-flash":{"draws":16,"losses":15,"wins":17},"google/gemma-4-31b-it":{"draws":1,"losses":0,"wins":9},"gpt-4.1":{"draws":8,"losses":0,"wins":0},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"gpt-5":{"draws":0,"losses":0,"wins":4},"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":14},"meta/muse-spark-1.2":{"draws":8,"losses":14,"wins":16},"meta/muse-spark-1.3":{"draws":11,"losses":26,"wins":15},"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":23,"wins":8},"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":0,"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":25,"wins":10},"x-ai/grok-4.6":{"draws":14,"losses":27,"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":2},"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":40},"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":6},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":32},"deepseek/deepseek-v4-pro":{"draws":0,"losses":4,"wins":32},"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":8,"wins":59},"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":0,"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":3},"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":16},"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":2},"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":5,"losses":0,"wins":37},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":6},"stealth/ox-alpha":{"draws":32,"losses":11,"wins":117},"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":0,"losses":0,"wins":14},"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":46},"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":3}},"gpt-6-luna":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"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":4,"losses":6,"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},"deepseek/deepseek-v4-flash":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro":{"draws":1,"losses":2,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":6,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":3,"losses":2,"wins":7},"google/gemini-3.5-flash":{"draws":2,"losses":6,"wins":6},"google/gemini-3.5-flash-lite":{"draws":7,"losses":3,"wins":8},"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":11,"wins":0},"gpt-5.6-terra":{"draws":1,"losses":2,"wins":3},"gpt-6-astra":{"draws":1,"losses":10,"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":3,"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":0,"wins":0},"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":1},"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":8,"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":1,"losses":3,"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":3,"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":5,"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":7,"wins":1},"z-ai/glm-5.3":{"draws":0,"losses":4,"wins":0},"z-ai/glm-5.3-flash":{"draws":3,"losses":6,"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":4,"wins":8},"claude-opus-5-5":{"draws":5,"losses":35,"wins":12},"claude-sonnet-5":{"draws":2,"losses":2,"wins":12},"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":10},"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":0,"wins":18},"google/gemini-3.6-flash":{"draws":2,"losses":1,"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":4},"gpt-5.4-mini":{"draws":2,"losses":0,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":0,"wins":2},"gpt-5.5":{"draws":2,"losses":1,"wins":9},"gpt-5.6-luna":{"draws":1,"losses":0,"wins":9},"gpt-5.6-sol":{"draws":2,"losses":5,"wins":1},"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":1},"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":4},"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":4},"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":12},"stepfun/step-3.7-flash":{"draws":0,"losses":0,"wins":6},"tencent/hy3-preview":{"draws":1,"losses":0,"wins":7},"tencent/hy4-preview":{"draws":0,"losses":2,"wins":2},"thinkingmachines/inkling":{"draws":0,"losses":0,"wins":8},"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":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":2,"losses":0,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":3,"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":8,"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":8,"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":8,"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":8,"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":16,"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":10,"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":8,"wins":0},"claude-opus-5":{"draws":2,"losses":18,"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":11,"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":12,"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":14,"wins":0},"minimax/minimax-m3":{"draws":2,"losses":6,"wins":2},"mistralai/mistral-medium-3-5":{"draws":15,"losses":7,"wins":4},"moonshotai/kimi-k2.7-code":{"draws":0,"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":2,"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":10,"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":17,"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":11,"wins":1},"z-ai/glm-5.3-flash":{"draws":10,"losses":13,"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":6,"losses":9,"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":15,"wins":20},"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":6},"google/gemini-3.5-flash":{"draws":14,"losses":23,"wins":5},"google/gemini-3.5-flash-lite":{"draws":50,"losses":95,"wins":39},"google/gemini-3.6-flash":{"draws":57,"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":6,"wins":2},"moonshotai/kimi-k3":{"draws":18,"losses":56,"wins":20},"nex-agi/nex-n2-pro":{"draws":2,"losses":3,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":4,"losses":2,"wins":10},"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":25,"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":8,"wins":7},"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":15},"claude-fable-5-1":{"draws":1,"losses":35,"wins":2},"claude-opus-4-5":{"draws":31,"losses":87,"wins":29},"claude-opus-4-8":{"draws":8,"losses":19,"wins":7},"claude-opus-5":{"draws":10,"losses":48,"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":49,"wins":10},"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":13,"losses":20,"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":63,"wins":19},"gpt-5.4-mini":{"draws":11,"losses":19,"wins":8},"gpt-5.4-nano":{"draws":6,"losses":17,"wins":11},"gpt-5.5":{"draws":12,"losses":18,"wins":7},"gpt-5.6-luna":{"draws":44,"losses":60,"wins":44},"gpt-5.6-sol":{"draws":21,"losses":94,"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":0},"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":26,"wins":20},"meta/muse-spark-1.2":{"draws":28,"losses":40,"wins":34},"meta/muse-spark-1.3":{"draws":18,"losses":28,"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":40,"losses":25,"wins":49},"qwen/qwen3.7-max":{"draws":2,"losses":14,"wins":1},"qwen/qwen3.7-plus":{"draws":4,"losses":5,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":15,"losses":39,"wins":10},"qwen/qwen3.8-27b":{"draws":7,"losses":25,"wins":12},"qwen/qwen3.8-flash":{"draws":17,"losses":21,"wins":8},"qwen/qwen3.8-max":{"draws":28,"losses":34,"wins":12},"qwen/qwen3.8-max-0902":{"draws":5,"losses":17,"wins":3},"stealth/ox-alpha":{"draws":52,"losses":108,"wins":28},"stepfun/step-3.7-flash":{"draws":13,"losses":28,"wins":23},"tencent/hy3-preview":{"draws":2,"losses":2,"wins":2},"tencent/hy4-preview":{"draws":19,"losses":37,"wins":8},"thinkingmachines/inkling":{"draws":32,"losses":53,"wins":45},"thinkingmachines/inkling-small":{"draws":18,"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":8,"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":31,"wins":35},"z-ai/glm-5.3":{"draws":20,"losses":30,"wins":6},"z-ai/glm-5.3-flash":{"draws":9,"losses":29,"wins":16},"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":17,"wins":14},"claude-fable-5":{"draws":8,"losses":10,"wins":2},"claude-fable-5-1":{"draws":1,"losses":19,"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":18,"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":14,"losses":23,"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":31,"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":12,"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":17,"wins":7},"gpt-6-astra":{"draws":1,"losses":11,"wins":0},"gpt-6-luna":{"draws":0,"losses":7,"wins":1},"gpt-6-sol":{"draws":2,"losses":4,"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":13,"wins":8},"meta/muse-spark-1.3":{"draws":12,"losses":10,"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":0,"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":3,"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":4,"losses":6,"wins":0},"stealth/ox-alpha":{"draws":46,"losses":68,"wins":16},"stepfun/step-3.7-flash":{"draws":6,"losses":2,"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":8,"losses":5,"wins":3},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"wins":2},"xiaomi/mimo-v2.6-flash":{"draws":0,"losses":4,"wins":2},"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":12},"claude-fable-5-1":{"draws":3,"losses":40,"wins":7},"claude-opus-4-5":{"draws":17,"losses":13,"wins":34},"claude-opus-4-8":{"draws":5,"losses":7,"wins":6},"claude-opus-5":{"draws":3,"losses":20,"wins":5},"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":19},"deepseek/deepseek-v4.1-flash":{"draws":6,"losses":4,"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":79},"google/gemini-3.8-flash":{"draws":4,"losses":14,"wins":28},"google/gemma-4-31b-it":{"draws":6,"losses":0,"wins":4},"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":1,"wins":3},"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":6,"losses":39,"wins":1},"gpt-6-luna":{"draws":2,"losses":1,"wins":3},"gpt-6-sol":{"draws":2,"losses":2,"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":15},"meta/muse-spark-1.2":{"draws":11,"losses":7,"wins":24},"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":11},"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":17,"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":13},"qwen/qwen3.8-max-0902":{"draws":1,"losses":6,"wins":3},"stealth/ox-alpha":{"draws":36,"losses":60,"wins":49},"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":25},"thinkingmachines/inkling-small":{"draws":18,"losses":3,"wins":17},"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":2,"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":1,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":1,"wins":1},"z-ai/glm-5.2":{"draws":12,"losses":21,"wins":25},"z-ai/glm-5.3":{"draws":10,"losses":26,"wins":12},"z-ai/glm-5.3-flash":{"draws":6,"losses":19,"wins":21},"z-ai/glm-5.3-flashx":{"draws":2,"losses":4,"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":0,"losses":9,"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":26},"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":38},"google/gemini-3.5-flash-lite":{"draws":7,"losses":13,"wins":38},"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":17,"wins":20},"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":13,"wins":25},"gpt-6-astra":{"draws":7,"losses":46,"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":8},"inclusionai/ling-3.0-flash":{"draws":1,"losses":3,"wins":8},"meituan/longcat-2.0":{"draws":5,"losses":4,"wins":23},"meta/muse-glimmer-30b":{"draws":5,"losses":0,"wins":9},"meta/muse-spark-1.2":{"draws":5,"losses":9,"wins":20},"meta/muse-spark-1.3":{"draws":6,"losses":8,"wins":12},"minimax/minimax-m3":{"draws":0,"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":47},"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":16,"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":25},"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":3,"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":1,"losses":3,"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":9,"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":6,"wins":4},"claude-fable-5":{"draws":2,"losses":6,"wins":0},"claude-fable-5-1":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":15,"losses":20,"wins":3},"claude-opus-4-8":{"draws":15,"losses":15,"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":2,"wins":0},"gpt-6-sol":{"draws":0,"losses":10,"wins":0},"inception/mercury-2.5-preview":{"draws":4,"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":0,"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":15,"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":2,"losses":2,"wins":2},"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":0},"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":0,"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":10,"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":9,"wins":5},"google/gemini-3.6-flash":{"draws":6,"losses":18,"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":0,"losses":8,"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":2,"losses":0,"wins":10},"inclusionai/ling-3.0-flash":{"draws":4,"losses":3,"wins":9},"meituan/longcat-2.0":{"draws":6,"losses":4,"wins":14},"meta/muse-glimmer-30b":{"draws":0,"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":13},"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":3,"wins":17},"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":3,"losses":5,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":4},"stealth/ox-alpha":{"draws":5,"losses":9,"wins":10},"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":10,"losses":19,"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":15,"losses":13,"wins":20},"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":2,"wins":6},"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":28,"losses":28,"wins":6},"google/gemma-4-31b-it":{"draws":0,"losses":3,"wins":11},"gpt-4.1":{"draws":2,"losses":0,"wins":0},"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":39,"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":26,"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":23,"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":48,"losses":68,"wins":45},"stepfun/step-3.7-flash":{"draws":15,"losses":3,"wins":20},"tencent/hy3-preview":{"draws":2,"losses":0,"wins":0},"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":20,"wins":18},"z-ai/glm-5.3":{"draws":9,"losses":34,"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":2},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":6,"wins":2},"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":1,"losses":6,"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":5,"wins":1},"gpt-5.4-mini":{"draws":5,"losses":8,"wins":5},"gpt-5.4-nano":{"draws":2,"losses":26,"wins":12},"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":25,"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":15},"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":13,"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":4,"losses":16,"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":11,"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":0},"gpt-5.4-mini":{"draws":17,"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":2,"wins":0},"inception/mercury-2.5-preview":{"draws":0,"losses":2,"wins":2},"inclusionai/ling-3.0-flash":{"draws":13,"losses":10,"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":5,"wins":1},"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":12,"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":0,"losses":7,"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":3,"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":0},"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":2,"wins":0},"z-ai/glm-5.3-flashx":{"draws":2,"losses":6,"wins":2}},"o3":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":2},"claude-fable-5":{"draws":2,"losses":7,"wins":1},"claude-fable-5-1":{"draws":0,"losses":5,"wins":1},"claude-opus-4-5":{"draws":17,"losses":32,"wins":17},"claude-opus-4-8":{"draws":7,"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":6,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":6,"losses":3,"wins":9},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":6,"losses":0,"wins":16},"google/gemini-3.5-flash":{"draws":5,"losses":10,"wins":11},"google/gemini-3.5-flash-lite":{"draws":8,"losses":3,"wins":29},"google/gemini-3.6-flash":{"draws":11,"losses":18,"wins":15},"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":2,"losses":8,"wins":2},"gpt-5.6-terra":{"draws":8,"losses":4,"wins":0},"gpt-6-astra":{"draws":0,"losses":12,"wins":0},"gpt-6-luna":{"draws":2,"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":8},"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":2,"wins":2},"qwen/qwen3.8-27b":{"draws":1,"losses":5,"wins":4},"qwen/qwen3.8-flash":{"draws":2,"losses":1,"wins":3},"qwen/qwen3.8-max":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":4},"stealth/ox-alpha":{"draws":11,"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":0,"losses":5,"wins":1},"thinkingmachines/inkling":{"draws":8,"losses":9,"wins":9},"thinkingmachines/inkling-small":{"draws":9,"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":34},"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":7,"losses":0,"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":24,"losses":15,"wins":15},"claude-fable-5":{"draws":9,"losses":23,"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":4,"wins":0},"claude-opus-5":{"draws":4,"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":28,"losses":37,"wins":27},"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":4,"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":2,"wins":8},"gpt-5.5":{"draws":6,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":25,"losses":21,"wins":12},"gpt-5.6-sol":{"draws":4,"losses":24,"wins":2},"gpt-5.6-terra":{"draws":20,"losses":26,"wins":2},"gpt-6-astra":{"draws":0,"losses":20,"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":13,"losses":16,"wins":11},"meta/muse-glimmer-30b":{"draws":23,"losses":15,"wins":14},"meta/muse-spark-1.2":{"draws":10,"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":9,"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":0,"losses":1,"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":12,"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":44,"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":2,"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":25,"losses":23,"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":4,"losses":4,"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":41,"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":14,"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":26,"wins":11},"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":31,"losses":32,"wins":11},"google/gemini-3.5-flash-lite":{"draws":167,"losses":87,"wins":94},"google/gemini-3.6-flash":{"draws":134,"losses":117,"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":4,"losses":1,"wins":3},"gpt-4.1-nano":{"draws":0,"losses":3,"wins":3},"gpt-5":{"draws":8,"losses":9,"wins":7},"gpt-5.4":{"draws":48,"losses":52,"wins":8},"gpt-5.4-mini":{"draws":17,"losses":12,"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":55,"losses":51,"wins":38},"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":22,"losses":24,"wins":6},"minimax/minimax-m3":{"draws":12,"losses":5,"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":65,"losses":77,"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":25,"wins":20},"qwen/qwen3.7-max":{"draws":10,"losses":9,"wins":5},"qwen/qwen3.7-plus":{"draws":14,"losses":3,"wins":3},"qwen/qwen3.8-2.4t-a95b":{"draws":30,"losses":24,"wins":6},"qwen/qwen3.8-27b":{"draws":9,"losses":20,"wins":9},"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":0},"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":22,"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":59,"losses":25,"wins":16},"z-ai/glm-5.3":{"draws":23,"losses":27,"wins":4},"z-ai/glm-5.3-flash":{"draws":36,"losses":24,"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":5,"losses":3,"wins":6},"claude-fable-5":{"draws":2,"losses":4,"wins":2},"claude-fable-5-1":{"draws":1,"losses":7,"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":45,"wins":16},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":0,"losses":8,"wins":2},"cohere/north-mini-code":{"draws":12,"losses":0,"wins":12},"deepseek/deepseek-v4-flash":{"draws":12,"losses":4,"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":6},"google/gemini-3.5-flash":{"draws":14,"losses":7,"wins":7},"google/gemini-3.5-flash-lite":{"draws":16,"losses":13,"wins":9},"google/gemini-3.6-flash":{"draws":5,"losses":18,"wins":7},"google/gemini-3.8-flash":{"draws":0,"losses":6,"wins":4},"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":15,"wins":11},"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":10,"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":4,"losses":1,"wins":1},"inclusionai/ling-3.0-flash":{"draws":18,"losses":3,"wins":13},"meituan/longcat-2.0":{"draws":16,"losses":3,"wins":24},"meta/muse-glimmer-30b":{"draws":4,"losses":4,"wins":4},"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":25,"losses":9,"wins":10},"o3":{"draws":11,"losses":11,"wins":10},"openai/gpt-oss-120b":{"draws":4,"losses":6,"wins":2},"poolside/laguna-s-2.1":{"draws":14,"losses":2,"wins":14},"qwen/qwen3.7-max":{"draws":6,"losses":2,"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":11,"wins":1},"qwen/qwen3.8-flash":{"draws":7,"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":21,"wins":7},"stepfun/step-3.7-flash":{"draws":8,"losses":3,"wins":13},"tencent/hy3-preview":{"draws":7,"losses":6,"wins":11},"tencent/hy4-preview":{"draws":2,"losses":8,"wins":4},"thinkingmachines/inkling":{"draws":18,"losses":7,"wins":17},"thinkingmachines/inkling-small":{"draws":3,"losses":5,"wins":6},"x-ai/grok-4.5":{"draws":12,"losses":11,"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":2,"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":5,"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":4,"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":10,"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":15,"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":5,"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":7,"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":4,"losses":0,"wins":0},"poolside/laguna-s-2.1":{"draws":22,"losses":10,"wins":4},"qwen/qwen3.7-max":{"draws":12,"losses":12,"wins":8},"qwen/qwen3.7-plus":{"draws":2,"losses":0,"wins":6},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"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":3,"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":8,"wins":0},"x-ai/grok-build-0.1":{"draws":8,"losses":1,"wins":11},"xiaomi/mimo-v2.5":{"draws":29,"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":36,"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":4,"losses":20,"wins":4},"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":19,"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":15},"google/gemini-3.5-flash-lite":{"draws":29,"losses":17,"wins":36},"google/gemini-3.6-flash":{"draws":23,"losses":37,"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":3,"wins":3},"gpt-5.4":{"draws":15,"losses":27,"wins":10},"gpt-5.4-mini":{"draws":2,"losses":1,"wins":5},"gpt-5.4-nano":{"draws":6,"losses":4,"wins":6},"gpt-5.5":{"draws":7,"losses":5,"wins":0},"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":12,"wins":12},"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":20},"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":4,"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":13},"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":11,"losses":19,"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":14,"losses":20,"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":12,"wins":13},"claude-fable-5":{"draws":2,"losses":17,"wins":3},"claude-fable-5-1":{"draws":0,"losses":20,"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":10,"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":3},"google/gemini-3.5-flash":{"draws":5,"losses":14,"wins":11},"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":1,"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":11,"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":15,"wins":11},"qwen/qwen3.7-max":{"draws":0,"losses":2,"wins":10},"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":14},"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":18},"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":0},"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":12,"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":18,"losses":19,"wins":13},"claude-fable-5-1":{"draws":1,"losses":49,"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":10,"losses":8,"wins":24},"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":2},"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":26,"losses":24,"wins":32},"google/gemini-3.8-flash":{"draws":12,"losses":12,"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":1},"gpt-5.4-nano":{"draws":8,"losses":0,"wins":4},"gpt-5.5":{"draws":4,"losses":9,"wins":5},"gpt-5.6-luna":{"draws":20,"losses":8,"wins":22},"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":1,"wins":3},"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":13,"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":12},"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":6},"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":5,"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":28,"wins":9},"z-ai/glm-5.3-flash":{"draws":13,"losses":11,"wins":28},"z-ai/glm-5.3-flashx":{"draws":3,"losses":6,"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":11},"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":6,"wins":4},"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":5,"wins":4},"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":27,"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":2},"gpt-5.6-luna":{"draws":19,"losses":8,"wins":15},"gpt-5.6-sol":{"draws":12,"losses":30,"wins":14},"gpt-5.6-terra":{"draws":22,"losses":15,"wins":15},"gpt-6-astra":{"draws":10,"losses":39,"wins":1},"gpt-6-luna":{"draws":4,"losses":0,"wins":2},"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":15},"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":4,"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":13,"wins":24},"qwen/qwen3.8-max-0902":{"draws":0,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":40,"losses":60,"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":10,"wins":15},"thinkingmachines/inkling-small":{"draws":30,"losses":31,"wins":40},"x-ai/grok-4.5":{"draws":9,"losses":19,"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":0,"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":8},"deepseek/deepseek-v4-pro":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":7,"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":6,"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":5,"losses":0,"wins":3},"meta/muse-spark-1.2":{"draws":3,"losses":3,"wins":4},"meta/muse-spark-1.3":{"draws":4,"losses":5,"wins":3},"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":2},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":1,"losses":0,"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":4,"wins":0},"qwen/qwen3.7-max":{"draws":3,"losses":0,"wins":3},"qwen/qwen3.7-plus":{"draws":0,"losses":1,"wins":1},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":2,"wins":3},"qwen/qwen3.8-27b":{"draws":0,"losses":4,"wins":0},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":0},"qwen/qwen3.8-max":{"draws":2,"losses":3,"wins":5},"qwen/qwen3.8-max-0902":{"draws":6,"losses":14,"wins":6},"stealth/ox-alpha":{"draws":7,"losses":21,"wins":10},"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":0,"losses":2,"wins":0},"x-ai/grok-4.6":{"draws":2,"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":2,"wins":6},"z-ai/glm-5.3":{"draws":2,"losses":6,"wins":0},"z-ai/glm-5.3-flash":{"draws":1,"losses":5,"wins":4},"z-ai/glm-5.3-flashx":{"draws":8,"losses":9,"wins":7}},"stealth/ox-alpha":{"bytedance-seed/seed-2.0-code":{"draws":27,"losses":37,"wins":64},"claude-fable-5":{"draws":42,"losses":74,"wins":32},"claude-fable-5-1":{"draws":18,"losses":167,"wins":5},"claude-opus-4-5":{"draws":48,"losses":46,"wins":50},"claude-opus-4-8":{"draws":12,"losses":13,"wins":21},"claude-opus-5":{"draws":13,"losses":58,"wins":17},"claude-opus-5-5":{"draws":5,"losses":31,"wins":2},"claude-sonnet-5":{"draws":44,"losses":50,"wins":70},"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":34,"losses":55,"wins":53},"deepseek/deepseek-v4.1-flash":{"draws":11,"losses":6,"wins":13},"google/gemini-3.1-flash-lite":{"draws":7,"losses":6,"wins":11},"google/gemini-3.5-flash":{"draws":40,"losses":46,"wins":62},"google/gemini-3.5-flash-lite":{"draws":60,"losses":58,"wins":130},"google/gemini-3.6-flash":{"draws":61,"losses":104,"wins":83},"google/gemini-3.8-flash":{"draws":33,"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":15,"wins":27},"gpt-5.4":{"draws":44,"losses":59,"wins":49},"gpt-5.4-mini":{"draws":10,"losses":7,"wins":11},"gpt-5.4-nano":{"draws":9,"losses":5,"wins":18},"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":105,"wins":34},"gpt-5.6-terra":{"draws":47,"losses":35,"wins":56},"gpt-6-astra":{"draws":20,"losses":135,"wins":7},"gpt-6-luna":{"draws":4,"losses":10,"wins":6},"gpt-6-sol":{"draws":5,"losses":22,"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":63,"wins":52},"nex-agi/nex-n2-pro":{"draws":8,"losses":3,"wins":23},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":0,"wins":22},"o3":{"draws":12,"losses":65,"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":2,"losses":4,"wins":8},"qwen/qwen3.7-plus":{"draws":3,"losses":3,"wins":8},"qwen/qwen3.8-2.4t-a95b":{"draws":51,"losses":63,"wins":46},"qwen/qwen3.8-27b":{"draws":17,"losses":39,"wins":30},"qwen/qwen3.8-flash":{"draws":23,"losses":29,"wins":32},"qwen/qwen3.8-max":{"draws":47,"losses":45,"wins":46},"qwen/qwen3.8-max-0902":{"draws":7,"losses":8,"wins":7},"stealth/ox-alpha":{"draws":129,"losses":270,"wins":195},"stepfun/step-3.7-flash":{"draws":3,"losses":9,"wins":22},"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":66},"thinkingmachines/inkling-small":{"draws":56,"losses":35,"wins":65},"x-ai/grok-4.5":{"draws":22,"losses":52,"wins":26},"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":14,"losses":9,"wins":31},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":11,"wins":15},"xiaomi/mimo-v2.6-flash":{"draws":5,"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":66,"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":2,"losses":0,"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":16,"losses":18,"wins":2},"gpt-5.5":{"draws":5,"losses":11,"wins":4},"gpt-5.6-luna":{"draws":6,"losses":0,"wins":0},"gpt-5.6-sol":{"draws":0,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":4,"losses":5,"wins":1},"gpt-6-astra":{"draws":0,"losses":8,"wins":0},"gpt-6-luna":{"draws":3,"losses":1,"wins":0},"gpt-6-sol":{"draws":0,"losses":2,"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":19,"wins":0},"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":2},"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":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":46},"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":21},"gpt-5.4-mini":{"draws":0,"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":18},"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":4},"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":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":2,"losses":9,"wins":35},"openai/gpt-oss-120b":{"draws":7,"losses":4,"wins":19},"poolside/laguna-s-2.1":{"draws":5,"losses":5,"wins":12},"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":25,"losses":46,"wins":62},"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":28},"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":4,"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":17,"wins":9},"claude-fable-5":{"draws":4,"losses":13,"wins":1},"claude-fable-5-1":{"draws":2,"losses":20,"wins":0},"claude-opus-4-5":{"draws":18,"losses":33,"wins":5},"claude-opus-4-8":{"draws":5,"losses":8,"wins":3},"claude-opus-5":{"draws":2,"losses":25,"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":9,"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":2,"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":19,"losses":10,"wins":5},"meta/muse-spark-1.2":{"draws":13,"losses":24,"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":16,"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":4,"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":6},"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":2,"losses":8,"wins":4},"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":4,"losses":6,"wins":0}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":16,"wins":10},"claude-fable-5":{"draws":14,"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":15,"losses":26,"wins":7},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":6},"deepseek/deepseek-v4-flash":{"draws":30,"losses":19,"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":22,"losses":35,"wins":19},"google/gemini-3.8-flash":{"draws":16,"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":2,"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":22,"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":23,"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":2,"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":33,"losses":51,"wins":17},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":54,"losses":75,"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":20,"wins":7},"thinkingmachines/inkling":{"draws":9,"losses":17,"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":10,"losses":3,"wins":5},"xiaomi/mimo-v2.5-pro":{"draws":4,"losses":2,"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":26,"losses":27,"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":4,"wins":4},"claude-fable-5-1":{"draws":0,"losses":9,"wins":1},"claude-opus-4-5":{"draws":20,"losses":16,"wins":26},"claude-opus-4-8":{"draws":11,"losses":18,"wins":25},"claude-opus-5":{"draws":15,"losses":62,"wins":21},"claude-opus-5-5":{"draws":2,"losses":14,"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":24},"deepseek/deepseek-v4-pro":{"draws":3,"losses":5,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":3,"losses":8,"wins":5},"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":7,"wins":13},"google/gemini-3.5-flash-lite":{"draws":7,"losses":11,"wins":36},"google/gemini-3.6-flash":{"draws":18,"losses":32,"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":3,"losses":17,"wins":24},"gpt-5.5":{"draws":18,"losses":15,"wins":23},"gpt-5.6-luna":{"draws":2,"losses":2,"wins":4},"gpt-5.6-sol":{"draws":2,"losses":15,"wins":11},"gpt-5.6-terra":{"draws":6,"losses":3,"wins":9},"gpt-6-astra":{"draws":3,"losses":15,"wins":0},"gpt-6-luna":{"draws":2,"losses":0,"wins":0},"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":11,"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":21},"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":11,"losses":12,"wins":13},"nex-agi/nex-n2-pro":{"draws":8,"losses":0,"wins":20},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":2,"wins":22},"o3":{"draws":4,"losses":8,"wins":14},"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":12,"losses":4,"wins":6},"qwen/qwen3.7-plus":{"draws":5,"losses":6,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":0,"losses":8,"wins":10},"qwen/qwen3.8-27b":{"draws":3,"losses":7,"wins":8},"qwen/qwen3.8-flash":{"draws":2,"losses":2,"wins":4},"qwen/qwen3.8-max":{"draws":3,"losses":7,"wins":6},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":6,"losses":16,"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":2},"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":19},"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":6},"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":8,"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":6},"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":13,"losses":15,"wins":36},"google/gemini-3.8-flash":{"draws":12,"losses":14,"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":3,"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":25},"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":11},"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":22},"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":22},"qwen/qwen3.8-27b":{"draws":4,"losses":6,"wins":16},"qwen/qwen3.8-flash":{"draws":8,"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":31,"losses":38,"wins":101},"stepfun/step-3.7-flash":{"draws":1,"losses":0,"wins":3},"tencent/hy3-preview":{"draws":3,"losses":1,"wins":4},"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":9},"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":1},"z-ai/glm-5.2":{"draws":11,"losses":6,"wins":21},"z-ai/glm-5.3":{"draws":11,"losses":22,"wins":23},"z-ai/glm-5.3-flash":{"draws":12,"losses":11,"wins":21},"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":4,"wins":0},"claude-opus-4-5":{"draws":0,"losses":1,"wins":9},"claude-opus-4-8":{"draws":0,"losses":2,"wins":2},"claude-opus-5":{"draws":1,"losses":4,"wins":5},"claude-opus-5-5":{"draws":1,"losses":16,"wins":5},"claude-sonnet-5":{"draws":0,"losses":1,"wins":7},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":2},"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":10},"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":4},"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":4},"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":4},"x-ai/grok-4.5":{"draws":0,"losses":2,"wins":8},"x-ai/grok-4.6":{"draws":2,"losses":2,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":1,"wins":7},"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":0,"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":4,"wins":17}},"x-ai/grok-build-0.1":{"bytedance-seed/seed-2.0-code":{"draws":3,"losses":7,"wins":2},"claude-fable-5":{"draws":2,"losses":10,"wins":4},"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":37,"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":6,"losses":4,"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":3,"wins":1},"gpt-5.4-mini":{"draws":26,"losses":18,"wins":12},"gpt-5.4-nano":{"draws":13,"losses":35,"wins":16},"gpt-5.5":{"draws":32,"losses":9,"wins":7},"gpt-5.6-luna":{"draws":6,"losses":4,"wins":0},"gpt-5.6-sol":{"draws":3,"losses":6,"wins":3},"gpt-5.6-terra":{"draws":6,"losses":8,"wins":4},"gpt-6-astra":{"draws":1,"losses":11,"wins":0},"gpt-6-luna":{"draws":7,"losses":5,"wins":0},"gpt-6-sol":{"draws":3,"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":10,"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":43,"losses":9,"wins":8},"o3":{"draws":8,"losses":20,"wins":2},"openai/gpt-oss-120b":{"draws":2,"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":1,"wins":1},"qwen/qwen3.8-max-0902":{"draws":4,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":13,"losses":25,"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":2,"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":65,"losses":66,"wins":21},"claude-opus-4-8":{"draws":29,"losses":41,"wins":10},"claude-opus-5":{"draws":21,"losses":81,"wins":10},"claude-opus-5-5":{"draws":1,"losses":15,"wins":0},"claude-sonnet-5":{"draws":12,"losses":7,"wins":1},"cohere/north-mini-code":{"draws":13,"losses":19,"wins":20},"deepseek/deepseek-v4-flash":{"draws":39,"losses":27,"wins":36},"deepseek/deepseek-v4-pro":{"draws":10,"losses":8,"wins":4},"deepseek/deepseek-v4-pro-0813":{"draws":10,"losses":4,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":4,"losses":14,"wins":0},"google/gemini-3.1-flash-lite":{"draws":28,"losses":19,"wins":43},"google/gemini-3.5-flash":{"draws":17,"losses":12,"wins":7},"google/gemini-3.5-flash-lite":{"draws":31,"losses":15,"wins":26},"google/gemini-3.6-flash":{"draws":33,"losses":29,"wins":8},"google/gemini-3.8-flash":{"draws":14,"losses":13,"wins":3},"google/gemma-4-31b-it":{"draws":11,"losses":23,"wins":20},"gpt-4.1":{"draws":8,"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":12,"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":6,"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":0,"losses":14,"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":14,"losses":14,"wins":16},"meituan/longcat-2.0":{"draws":37,"losses":33,"wins":34},"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":17,"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":41,"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":19,"losses":33,"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":14,"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":96,"losses":41,"wins":41},"xiaomi/mimo-v2.5-pro":{"draws":27,"losses":21,"wins":14},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":8,"wins":1},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.2":{"draws":51,"losses":49,"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":10,"losses":8,"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":0},"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":12},"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":2},"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":10,"losses":20,"wins":16},"google/gemini-3.8-flash":{"draws":4,"losses":5,"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},"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":9,"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":14},"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":2},"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":4},"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":17,"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":0,"losses":9,"wins":1},"claude-sonnet-5":{"draws":2,"losses":3,"wins":3},"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":2,"wins":4},"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":11,"wins":7},"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":5,"losses":12,"wins":1},"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":1,"losses":1,"wins":4},"meituan/longcat-2.0":{"draws":6,"losses":1,"wins":1},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"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":2,"losses":0,"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":20},"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":0,"wins":3},"x-ai/grok-4.6":{"draws":1,"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":1,"wins":19},"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":3},"z-ai/glm-5.2":{"draws":4,"losses":2,"wins":8},"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":20}},"xiaomi/mimo-v2.6-pro":{"bytedance-seed/seed-2.0-code":{"draws":1,"losses":2,"wins":9},"claude-fable-5":{"draws":1,"losses":3,"wins":4},"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":4},"claude-opus-5":{"draws":2,"losses":0,"wins":4},"claude-opus-5-5":{"draws":9,"losses":7,"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":0,"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":0,"wins":2},"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":1,"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":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":6},"x-ai/grok-4.7":{"draws":3,"losses":2,"wins":9},"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":1,"losses":2,"wins":13}},"z-ai/glm-5.2":{"bytedance-seed/seed-2.0-code":{"draws":20,"losses":13,"wins":19},"claude-fable-5":{"draws":21,"losses":27,"wins":12},"claude-fable-5-1":{"draws":7,"losses":39,"wins":2},"claude-opus-4-5":{"draws":29,"losses":32,"wins":39},"claude-opus-4-8":{"draws":29,"losses":33,"wins":24},"claude-opus-5":{"draws":13,"losses":59,"wins":2},"claude-opus-5-5":{"draws":1,"losses":16,"wins":1},"claude-sonnet-5":{"draws":16,"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":31},"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":12,"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":3,"wins":5},"gpt-5.4-nano":{"draws":24,"losses":16,"wins":24},"gpt-5.5":{"draws":28,"losses":24,"wins":12},"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":42,"wins":4},"gpt-6-luna":{"draws":6,"losses":3,"wins":9},"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":24},"meta/muse-glimmer-30b":{"draws":19,"losses":11,"wins":20},"meta/muse-spark-1.2":{"draws":6,"losses":23,"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":8,"losses":3,"wins":7},"moonshotai/kimi-k3":{"draws":23,"losses":11,"wins":12},"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":21,"wins":40},"openai/gpt-oss-120b":{"draws":22,"losses":7,"wins":13},"poolside/laguna-s-2.1":{"draws":39,"losses":10,"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":16,"losses":14,"wins":8},"qwen/qwen3.8-max":{"draws":23,"losses":21,"wins":16},"qwen/qwen3.8-max-0902":{"draws":8,"losses":4,"wins":0},"stealth/ox-alpha":{"draws":62,"losses":86,"wins":54},"stepfun/step-3.7-flash":{"draws":7,"losses":7,"wins":26},"tencent/hy3-preview":{"draws":18,"losses":6,"wins":8},"tencent/hy4-preview":{"draws":20,"losses":27,"wins":13},"thinkingmachines/inkling":{"draws":25,"losses":8,"wins":27},"thinkingmachines/inkling-small":{"draws":19,"losses":11,"wins":24},"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":0},"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":19},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":1,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":2,"wins":2},"z-ai/glm-5.2":{"draws":39,"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":2}},"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":3,"losses":1,"wins":10},"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":26},"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":7,"losses":13,"wins":38},"google/gemini-3.5-flash-lite":{"draws":8,"losses":3,"wins":51},"google/gemini-3.6-flash":{"draws":10,"losses":15,"wins":53},"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":28},"gpt-5.4-mini":{"draws":3,"losses":1,"wins":8},"gpt-5.4-nano":{"draws":0,"losses":5,"wins":9},"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":26},"nex-agi/nex-n2-pro":{"draws":2,"losses":1,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":2,"wins":6},"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":3,"wins":17},"qwen/qwen3.8-max":{"draws":10,"losses":8,"wins":24},"qwen/qwen3.8-max-0902":{"draws":5,"losses":3,"wins":4},"stealth/ox-alpha":{"draws":23,"losses":39,"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":19,"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":6,"losses":27,"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":9,"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":4},"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-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":24,"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":4},"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":9},"inclusionai/ling-3.0-flash":{"draws":5,"losses":1,"wins":6},"meituan/longcat-2.0":{"draws":7,"losses":1,"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":2},"mistralai/mistral-medium-3-5":{"draws":10,"losses":2,"wins":4},"moonshotai/kimi-k3":{"draws":14,"losses":12,"wins":20},"nex-agi/nex-n2-pro":{"draws":0,"losses":1,"wins":3},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":2,"losses":0,"wins":8},"o3":{"draws":10,"losses":16,"wins":26},"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":13},"qwen/qwen3.8-max-0902":{"draws":0,"losses":0,"wins":2},"stealth/ox-alpha":{"draws":32,"losses":54,"wins":79},"stepfun/step-3.7-flash":{"draws":2,"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":4},"claude-fable-5":{"draws":4,"losses":4,"wins":4},"claude-fable-5-1":{"draws":1,"losses":11,"wins":2},"claude-opus-4-5":{"draws":1,"losses":0,"wins":7},"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":2,"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":9},"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":1,"wins":1},"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-sol":{"draws":4,"losses":4,"wins":0},"gpt-5.6-terra":{"draws":0,"losses":2,"wins":0},"gpt-6-astra":{"draws":0,"losses":7,"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":4,"losses":3,"wins":3},"meta/muse-glimmer-30b":{"draws":2,"losses":4,"wins":2},"meta/muse-spark-1.2":{"draws":0,"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":2},"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":5},"qwen/qwen3.8-max":{"draws":6,"losses":2,"wins":2},"qwen/qwen3.8-max-0902":{"draws":7,"losses":19,"wins":10},"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":2,"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":4,"wins":0},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":4},"xiaomi/mimo-v2.5":{"draws":7,"losses":1,"wins":10},"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":9,"wins":3}}},"none":{"bytedance-seed/seed-2.0-code":{"bytedance-seed/seed-2.0-code":{"draws":11,"losses":16,"wins":5},"claude-fable-5":{"draws":4,"losses":11,"wins":3},"claude-fable-5-1":{"draws":1,"losses":15,"wins":0},"claude-opus-4-5":{"draws":11,"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":30,"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":23,"losses":39,"wins":22},"google/gemini-3.6-flash":{"draws":16,"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":5,"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":9,"losses":15,"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":33,"wins":8},"openai/gpt-oss-120b":{"draws":17,"losses":19,"wins":12},"poolside/laguna-s-2.1":{"draws":9,"losses":9,"wins":10},"qwen/qwen3.7-max":{"draws":2,"losses":2,"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":12,"wins":5},"qwen/qwen3.8-flash":{"draws":13,"losses":13,"wins":2},"qwen/qwen3.8-max":{"draws":17,"losses":16,"wins":7},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"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":17,"wins":12},"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":12,"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":8,"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":5,"wins":1}},"claude-fable-5":{"bytedance-seed/seed-2.0-code":{"draws":10,"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":27},"claude-opus-4-8":{"draws":2,"losses":4,"wins":2},"claude-opus-5":{"draws":5,"losses":27,"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":2},"deepseek/deepseek-v4-flash":{"draws":13,"losses":9,"wins":30},"deepseek/deepseek-v4-pro":{"draws":15,"losses":11,"wins":14},"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":11,"wins":20},"google/gemini-3.5-flash-lite":{"draws":21,"losses":11,"wins":42},"google/gemini-3.6-flash":{"draws":20,"losses":22,"wins":36},"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":18,"losses":9,"wins":19},"gpt-5.6-sol":{"draws":9,"losses":26,"wins":13},"gpt-5.6-terra":{"draws":11,"losses":10,"wins":27},"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":9},"inclusionai/ling-3.0-flash":{"draws":6,"losses":1,"wins":7},"meituan/longcat-2.0":{"draws":7,"losses":9,"wins":12},"meta/muse-glimmer-30b":{"draws":16,"losses":2,"wins":12},"meta/muse-spark-1.2":{"draws":10,"losses":9,"wins":13},"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":11,"losses":1,"wins":6},"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":14},"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":15,"wins":22},"qwen/qwen3.8-max-0902":{"draws":5,"losses":1,"wins":2},"stealth/ox-alpha":{"draws":32,"losses":43,"wins":71},"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":24},"thinkingmachines/inkling-small":{"draws":13,"losses":4,"wins":17},"x-ai/grok-4.5":{"draws":7,"losses":17,"wins":16},"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":0,"wins":10},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":2,"wins":5},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":2,"wins":8},"z-ai/glm-5.2":{"draws":21,"losses":14,"wins":15},"z-ai/glm-5.3":{"draws":8,"losses":34,"wins":12},"z-ai/glm-5.3-flash":{"draws":7,"losses":22,"wins":9},"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":32,"wins":11},"claude-opus-4-5":{"draws":2,"losses":0,"wins":34},"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":28},"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":39},"google/gemini-3.5-flash-lite":{"draws":7,"losses":0,"wins":45},"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":5,"losses":2,"wins":21},"gpt-5.6-sol":{"draws":9,"losses":9,"wins":34},"gpt-5.6-terra":{"draws":8,"losses":0,"wins":36},"gpt-6-astra":{"draws":9,"losses":37,"wins":12},"gpt-6-luna":{"draws":1,"losses":0,"wins":7},"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":9},"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":17},"qwen/qwen3.8-flash":{"draws":3,"losses":2,"wins":19},"qwen/qwen3.8-max":{"draws":5,"losses":2,"wins":33},"qwen/qwen3.8-max-0902":{"draws":0,"losses":0,"wins":16},"stealth/ox-alpha":{"draws":24,"losses":8,"wins":120},"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":0,"wins":2},"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":0,"losses":2,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"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":1,"wins":6}},"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":66,"wins":8},"claude-opus-5-5":{"draws":0,"losses":10,"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":6,"wins":7},"google/gemini-3.5-flash-lite":{"draws":22,"losses":16,"wins":16},"google/gemini-3.6-flash":{"draws":13,"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":0},"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":6,"wins":16},"meta/muse-glimmer-30b":{"draws":2,"losses":2,"wins":6},"meta/muse-spark-1.2":{"draws":0,"losses":2,"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":5,"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":25,"losses":25,"wins":14},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"wins":8},"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":0,"wins":6},"x-ai/grok-4.5":{"draws":11,"losses":13,"wins":12},"x-ai/grok-4.6":{"draws":5,"losses":7,"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":12,"wins":42},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":13,"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":5,"wins":3},"claude-fable-5-1":{"draws":2,"losses":8,"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":12,"losses":36,"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":19},"google/gemini-3.5-flash":{"draws":15,"losses":7,"wins":10},"google/gemini-3.5-flash-lite":{"draws":13,"losses":9,"wins":12},"google/gemini-3.6-flash":{"draws":13,"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":10},"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":2,"wins":0},"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":13},"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":11,"wins":3},"nex-agi/nex-n2-pro":{"draws":10,"losses":6,"wins":12},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":6,"wins":23},"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":6,"wins":5},"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":3,"wins":1},"x-ai/grok-build-0.1":{"draws":6,"losses":0,"wins":8},"xiaomi/mimo-v2.5":{"draws":23,"losses":15,"wins":42},"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":4,"wins":0},"z-ai/glm-5.2":{"draws":27,"losses":25,"wins":18},"z-ai/glm-5.3":{"draws":4,"losses":12,"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":27},"claude-fable-5-1":{"draws":2,"losses":12,"wins":6},"claude-opus-4-5":{"draws":35,"losses":28,"wins":85},"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":10,"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":11},"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":32},"google/gemini-3.5-flash-lite":{"draws":11,"losses":6,"wins":67},"google/gemini-3.6-flash":{"draws":23,"losses":23,"wins":62},"google/gemini-3.8-flash":{"draws":8,"losses":13,"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":74},"gpt-5.5":{"draws":22,"losses":30,"wins":68},"gpt-5.6-luna":{"draws":5,"losses":3,"wins":18},"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":2,"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":8},"inclusionai/ling-3.0-flash":{"draws":20,"losses":1,"wins":35},"meituan/longcat-2.0":{"draws":14,"losses":6,"wins":62},"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":39},"openai/gpt-oss-120b":{"draws":4,"losses":0,"wins":10},"poolside/laguna-s-2.1":{"draws":12,"losses":6,"wins":72},"qwen/qwen3.7-max":{"draws":8,"losses":10,"wins":38},"qwen/qwen3.7-plus":{"draws":13,"losses":8,"wins":15},"qwen/qwen3.8-2.4t-a95b":{"draws":9,"losses":13,"wins":30},"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":9,"losses":8,"wins":19},"qwen/qwen3.8-max-0902":{"draws":2,"losses":5,"wins":9},"stealth/ox-alpha":{"draws":19,"losses":21,"wins":52},"stepfun/step-3.7-flash":{"draws":6,"losses":0,"wins":30},"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":31},"thinkingmachines/inkling-small":{"draws":0,"losses":1,"wins":17},"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":12},"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":1,"losses":0,"wins":7},"xiaomi/mimo-v2.6-pro":{"draws":3,"losses":2,"wins":5},"z-ai/glm-5.2":{"draws":33,"losses":9,"wins":70},"z-ai/glm-5.3":{"draws":7,"losses":9,"wins":14},"z-ai/glm-5.3-flash":{"draws":0,"losses":8,"wins":20},"z-ai/glm-5.3-flashx":{"draws":4,"losses":5,"wins":7}},"claude-opus-5-5":{"bytedance-seed/seed-2.0-code":{"draws":0,"losses":2,"wins":4},"claude-fable-5":{"draws":1,"losses":1,"wins":4},"claude-fable-5-1":{"draws":2,"losses":8,"wins":4},"claude-opus-4-5":{"draws":4,"losses":3,"wins":13},"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":11},"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":8},"google/gemini-3.5-flash-lite":{"draws":5,"losses":0,"wins":11},"google/gemini-3.6-flash":{"draws":4,"losses":0,"wins":10},"google/gemini-3.8-flash":{"draws":3,"losses":1,"wins":4},"google/gemma-4-31b-it":{"draws":0,"losses":0,"wins":6},"gpt-4.1":{"draws":0,"losses":0,"wins":2},"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":0,"losses":0,"wins":4},"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":0,"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":13},"openai/gpt-oss-120b":{"draws":1,"losses":0,"wins":9},"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":1,"losses":0,"wins":1},"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":11},"stealth/ox-alpha":{"draws":6,"losses":1,"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":12},"thinkingmachines/inkling-small":{"draws":5,"losses":0,"wins":3},"x-ai/grok-4.5":{"draws":3,"losses":4,"wins":9},"x-ai/grok-4.6":{"draws":2,"losses":4,"wins":6},"x-ai/grok-4.7":{"draws":2,"losses":9,"wins":19},"x-ai/grok-build-0.1":{"draws":0,"losses":0,"wins":2},"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":4,"losses":1,"wins":13},"xiaomi/mimo-v2.6-pro":{"draws":9,"losses":7,"wins":10},"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":16},"claude-fable-5":{"draws":14,"losses":27,"wins":3},"claude-fable-5-1":{"draws":5,"losses":39,"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":16,"wins":27},"deepseek/deepseek-v4-pro":{"draws":19,"losses":17,"wins":10},"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":19,"losses":27,"wins":12},"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":4,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":4,"wins":2},"gpt-5.5":{"draws":2,"losses":5,"wins":1},"gpt-5.6-luna":{"draws":41,"losses":29,"wins":36},"gpt-5.6-sol":{"draws":17,"losses":84,"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":20},"meituan/longcat-2.0":{"draws":18,"losses":9,"wins":29},"meta/muse-glimmer-30b":{"draws":19,"losses":8,"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":32,"losses":41,"wins":15},"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":6},"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":14,"losses":24,"wins":10},"thinkingmachines/inkling":{"draws":24,"losses":8,"wins":34},"thinkingmachines/inkling-small":{"draws":14,"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":11,"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":2,"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":13,"losses":6,"wins":1},"google/gemini-3.6-flash":{"draws":11,"losses":25,"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":2,"wins":0},"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":0,"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":12,"losses":5,"wins":7},"openai/gpt-oss-120b":{"draws":0,"losses":2,"wins":0},"poolside/laguna-s-2.1":{"draws":21,"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":4,"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":13,"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":3,"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":19,"wins":9},"google/gemini-3.5-flash-lite":{"draws":28,"losses":36,"wins":30},"google/gemini-3.6-flash":{"draws":15,"losses":45,"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":2,"wins":0},"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":19,"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":11,"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":19,"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":60,"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":21,"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":5,"losses":15,"wins":4},"claude-opus-4-8":{"draws":2,"losses":4,"wins":0},"claude-opus-5":{"draws":0,"losses":14,"wins":4},"claude-opus-5-5":{"draws":0,"losses":10,"wins":0},"claude-sonnet-5":{"draws":12,"losses":11,"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":12,"wins":15},"google/gemini-3.5-flash-lite":{"draws":33,"losses":18,"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":0,"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":1,"losses":0,"wins":1},"gpt-5.5":{"draws":1,"losses":4,"wins":1},"gpt-5.6-luna":{"draws":12,"losses":13,"wins":13},"gpt-5.6-sol":{"draws":3,"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},"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":7},"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":13,"losses":12,"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":3,"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":10,"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":6,"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":11,"losses":21,"wins":2},"gpt-4.1":{"draws":3,"losses":2,"wins":1},"gpt-4.1-nano":{"draws":0,"losses":2,"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":0,"losses":2,"wins":4},"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":7,"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":0},"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":19,"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":17,"losses":13,"wins":12},"z-ai/glm-5.3":{"draws":2,"losses":19,"wins":3},"z-ai/glm-5.3-flash":{"draws":13,"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":10,"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":8,"losses":4,"wins":8},"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":8,"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":8,"losses":5,"wins":3},"gpt-6-sol":{"draws":2,"losses":6,"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":2,"losses":2,"wins":0},"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":4,"wins":0},"openai/gpt-oss-120b":{"draws":5,"losses":3,"wins":2},"poolside/laguna-s-2.1":{"draws":3,"losses":3,"wins":2},"qwen/qwen3.7-max":{"draws":2,"losses":2,"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":6,"losses":11,"wins":1},"stealth/ox-alpha":{"draws":6,"losses":21,"wins":7},"stepfun/step-3.7-flash":{"draws":2,"losses":2,"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},"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":2,"wins":2},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":1},"xiaomi/mimo-v2.5":{"draws":9,"losses":1,"wins":2},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":2,"losses":4,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":5,"wins":1},"z-ai/glm-5.2":{"draws":7,"losses":8,"wins":3},"z-ai/glm-5.3":{"draws":3,"losses":7,"wins":2},"z-ai/glm-5.3-flash":{"draws":0,"losses":2,"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":6,"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":9,"wins":0},"gpt-6-astra":{"draws":0,"losses":2,"wins":0},"gpt-6-luna":{"draws":1,"losses":3,"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":1,"losses":9,"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":9,"wins":1},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":10,"losses":26,"wins":6},"o3":{"draws":0,"losses":14,"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":4,"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":6,"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":10,"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":19,"wins":17},"claude-fable-5":{"draws":12,"losses":22,"wins":4},"claude-fable-5-1":{"draws":3,"losses":21,"wins":0},"claude-opus-4-5":{"draws":16,"losses":30,"wins":20},"claude-opus-4-8":{"draws":22,"losses":20,"wins":2},"claude-opus-5":{"draws":6,"losses":42,"wins":6},"claude-opus-5-5":{"draws":0,"losses":14,"wins":0},"claude-sonnet-5":{"draws":21,"losses":29,"wins":14},"cohere/north-mini-code":{"draws":7,"losses":3,"wins":6},"deepseek/deepseek-v4-flash":{"draws":30,"losses":24,"wins":20},"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":45,"losses":51,"wins":36},"google/gemini-3.6-flash":{"draws":24,"losses":43,"wins":21},"google/gemini-3.8-flash":{"draws":12,"losses":36,"wins":2},"google/gemma-4-31b-it":{"draws":10,"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":5,"wins":8},"gpt-5.4-nano":{"draws":16,"losses":15,"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":19,"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":16},"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":26,"wins":6},"minimax/minimax-m3":{"draws":9,"losses":9,"wins":4},"mistralai/mistral-medium-3-5":{"draws":13,"losses":7,"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":2,"wins":7},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":17,"losses":8,"wins":5},"o3":{"draws":13,"losses":29,"wins":34},"openai/gpt-oss-120b":{"draws":19,"losses":17,"wins":16},"poolside/laguna-s-2.1":{"draws":24,"losses":12,"wins":10},"qwen/qwen3.7-max":{"draws":10,"losses":11,"wins":9},"qwen/qwen3.7-plus":{"draws":8,"losses":2,"wins":4},"qwen/qwen3.8-2.4t-a95b":{"draws":16,"losses":27,"wins":7},"qwen/qwen3.8-27b":{"draws":7,"losses":17,"wins":6},"qwen/qwen3.8-flash":{"draws":20,"losses":8,"wins":10},"qwen/qwen3.8-max":{"draws":21,"losses":10,"wins":13},"qwen/qwen3.8-max-0902":{"draws":6,"losses":2,"wins":2},"stealth/ox-alpha":{"draws":32,"losses":90,"wins":26},"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":25,"wins":6},"x-ai/grok-4.6":{"draws":12,"losses":24,"wins":4},"x-ai/grok-4.7":{"draws":0,"losses":11,"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":5,"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":8,"losses":31,"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":17,"losses":59,"wins":14},"claude-fable-5-1":{"draws":9,"losses":72,"wins":1},"claude-opus-4-5":{"draws":64,"losses":67,"wins":57},"claude-opus-4-8":{"draws":9,"losses":15,"wins":10},"claude-opus-5":{"draws":12,"losses":85,"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":11,"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":36,"losses":39,"wins":29},"google/gemini-3.5-flash-lite":{"draws":132,"losses":107,"wins":125},"google/gemini-3.6-flash":{"draws":138,"losses":159,"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":12,"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":62,"losses":64,"wins":68},"gpt-5.6-sol":{"draws":19,"losses":131,"wins":26},"gpt-5.6-terra":{"draws":32,"losses":34,"wins":30},"gpt-6-astra":{"draws":2,"losses":74,"wins":0},"gpt-6-luna":{"draws":4,"losses":11,"wins":5},"gpt-6-sol":{"draws":3,"losses":20,"wins":1},"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":66},"meituan/longcat-2.0":{"draws":47,"losses":46,"wins":86},"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":45,"wins":22},"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":5},"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":87,"wins":100},"openai/gpt-oss-120b":{"draws":29,"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":4,"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":72,"losses":120,"wins":66},"stepfun/step-3.7-flash":{"draws":14,"losses":15,"wins":23},"tencent/hy3-preview":{"draws":16,"losses":10,"wins":4},"tencent/hy4-preview":{"draws":37,"losses":36,"wins":17},"thinkingmachines/inkling":{"draws":78,"losses":53,"wins":71},"thinkingmachines/inkling-small":{"draws":43,"losses":24,"wins":43},"x-ai/grok-4.5":{"draws":47,"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":63,"wins":8},"z-ai/glm-5.3-flash":{"draws":26,"losses":53,"wins":17},"z-ai/glm-5.3-flashx":{"draws":4,"losses":8,"wins":2}},"google/gemini-3.6-flash":{"bytedance-seed/seed-2.0-code":{"draws":31,"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":66,"losses":83,"wins":41},"claude-opus-4-8":{"draws":9,"losses":11,"wins":10},"claude-opus-5":{"draws":11,"losses":62,"wins":11},"claude-opus-5-5":{"draws":1,"losses":17,"wins":0},"claude-sonnet-5":{"draws":65,"losses":79,"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":37,"wins":18},"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":30,"losses":36,"wins":22},"google/gemini-3.5-flash-lite":{"draws":194,"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":12,"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":21,"losses":19,"wins":12},"gpt-5.5":{"draws":20,"losses":16,"wins":12},"gpt-5.6-luna":{"draws":84,"losses":51,"wins":67},"gpt-5.6-sol":{"draws":27,"losses":121,"wins":16},"gpt-5.6-terra":{"draws":38,"losses":32,"wins":24},"gpt-6-astra":{"draws":5,"losses":57,"wins":0},"gpt-6-luna":{"draws":3,"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":67,"losses":31,"wins":46},"meituan/longcat-2.0":{"draws":57,"losses":42,"wins":71},"meta/muse-glimmer-30b":{"draws":51,"losses":17,"wins":36},"meta/muse-spark-1.2":{"draws":33,"losses":79,"wins":28},"meta/muse-spark-1.3":{"draws":25,"losses":40,"wins":15},"minimax/minimax-m3":{"draws":6,"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":88,"losses":103,"wins":27},"nex-agi/nex-n2-pro":{"draws":14,"losses":5,"wins":17},"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":13,"losses":3,"wins":16},"qwen/qwen3.7-plus":{"draws":11,"losses":8,"wins":7},"qwen/qwen3.8-2.4t-a95b":{"draws":33,"losses":32,"wins":21},"qwen/qwen3.8-27b":{"draws":12,"losses":19,"wins":23},"qwen/qwen3.8-flash":{"draws":32,"losses":17,"wins":15},"qwen/qwen3.8-max":{"draws":34,"losses":49,"wins":25},"qwen/qwen3.8-max-0902":{"draws":6,"losses":1,"wins":3},"stealth/ox-alpha":{"draws":79,"losses":141,"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":49,"wins":23},"thinkingmachines/inkling":{"draws":102,"losses":30,"wins":100},"thinkingmachines/inkling-small":{"draws":42,"losses":36,"wins":33},"x-ai/grok-4.5":{"draws":48,"losses":98,"wins":58},"x-ai/grok-4.6":{"draws":28,"losses":33,"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":1,"losses":11,"wins":8},"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":44,"losses":42,"wins":32},"z-ai/glm-5.3":{"draws":14,"losses":59,"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":8,"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":12,"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":30,"wins":31},"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":1,"losses":5,"wins":2},"gpt-5.4-nano":{"draws":3,"losses":2,"wins":13},"gpt-5.5":{"draws":4,"losses":3,"wins":3},"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":15,"losses":1,"wins":12},"inclusionai/ling-3.0-flash":{"draws":6,"losses":0,"wins":12},"meituan/longcat-2.0":{"draws":7,"losses":4,"wins":11},"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":21},"moonshotai/kimi-k2.7-code":{"draws":0,"losses":0,"wins":2},"moonshotai/kimi-k3":{"draws":16,"losses":10,"wins":16},"nex-agi/nex-n2-pro":{"draws":0,"losses":2,"wins":2},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":3,"losses":3,"wins":6},"o3":{"draws":6,"losses":16,"wins":26},"openai/gpt-oss-120b":{"draws":7,"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":17,"losses":15,"wins":18},"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":14,"losses":14,"wins":20},"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":6,"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":6,"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":24,"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":8,"wins":1},"cohere/north-mini-code":{"draws":9,"losses":6,"wins":11},"deepseek/deepseek-v4-flash":{"draws":14,"losses":27,"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":1,"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":11,"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":1,"losses":6,"wins":1},"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":10,"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":18,"wins":3},"stepfun/step-3.7-flash":{"draws":2,"losses":10,"wins":4},"tencent/hy3-preview":{"draws":12,"losses":13,"wins":5},"tencent/hy4-preview":{"draws":2,"losses":8,"wins":0},"thinkingmachines/inkling":{"draws":8,"losses":16,"wins":4},"thinkingmachines/inkling-small":{"draws":3,"losses":2,"wins":1},"x-ai/grok-4.5":{"draws":2,"losses":10,"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":10,"wins":4},"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":18,"losses":24,"wins":6},"claude-opus-5":{"draws":12,"losses":70,"wins":7},"claude-opus-5-5":{"draws":0,"losses":4,"wins":0},"claude-sonnet-5":{"draws":3,"losses":2,"wins":1},"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":1,"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":17,"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":8,"losses":3,"wins":3},"gpt-6-astra":{"draws":4,"losses":10,"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":9,"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":10,"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":38,"losses":20,"wins":36},"xiaomi/mimo-v2.5-pro":{"draws":5,"losses":9,"wins":18},"xiaomi/mimo-v2.6-flash":{"draws":6,"losses":3,"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":0},"z-ai/glm-5.3-flashx":{"draws":8,"losses":7,"wins":3}},"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":3},"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":14,"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":3,"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":14,"wins":0},"claude-opus-4-5":{"draws":4,"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":4,"losses":4,"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":4},"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":9,"wins":3},"gpt-5.6-terra":{"draws":0,"losses":5,"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":6},"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":2,"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":2,"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":6},"thinkingmachines/inkling-small":{"draws":3,"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":2,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":0,"wins":2},"z-ai/glm-5.2":{"draws":8,"losses":13,"wins":9},"z-ai/glm-5.3":{"draws":3,"losses":6,"wins":1},"z-ai/glm-5.3-flash":{"draws":6,"losses":4,"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":22,"wins":22},"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":7,"losses":1,"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":2},"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":3,"wins":4},"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":4,"losses":2,"wins":6},"gpt-6-sol":{"draws":2,"losses":2,"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":19},"meta/muse-glimmer-30b":{"draws":14,"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":2},"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":3},"qwen/qwen3.8-2.4t-a95b":{"draws":13,"losses":20,"wins":13},"qwen/qwen3.8-27b":{"draws":8,"losses":9,"wins":11},"qwen/qwen3.8-flash":{"draws":12,"losses":14,"wins":4},"qwen/qwen3.8-max":{"draws":13,"losses":18,"wins":11},"qwen/qwen3.8-max-0902":{"draws":3,"losses":0,"wins":1},"stealth/ox-alpha":{"draws":54,"losses":66,"wins":40},"stepfun/step-3.7-flash":{"draws":8,"losses":3,"wins":13},"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":23,"losses":4,"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":7,"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":23,"wins":12},"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":12,"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":2,"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":18,"wins":9},"google/gemini-3.6-flash":{"draws":20,"losses":21,"wins":5},"google/gemini-3.8-flash":{"draws":1,"losses":6,"wins":1},"google/gemma-4-31b-it":{"draws":5,"losses":13,"wins":4},"gpt-4.1":{"draws":10,"losses":1,"wins":9},"gpt-5":{"draws":17,"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":27,"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},"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":25,"losses":7,"wins":8},"meituan/longcat-2.0":{"draws":23,"losses":20,"wins":9},"meta/muse-glimmer-30b":{"draws":8,"losses":3,"wins":3},"meta/muse-spark-1.2":{"draws":0,"losses":6,"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":33,"losses":14,"wins":7},"o3":{"draws":5,"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":9,"wins":4},"tencent/hy4-preview":{"draws":5,"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":5,"losses":7,"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":21,"wins":5},"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":12,"wins":0},"claude-opus-4-5":{"draws":25,"losses":53,"wins":24},"claude-opus-4-8":{"draws":21,"losses":49,"wins":14},"claude-opus-5":{"draws":16,"losses":88,"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":20,"losses":33,"wins":17},"deepseek/deepseek-v4-pro":{"draws":7,"losses":8,"wins":3},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":6,"wins":2},"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":2},"google/gemini-3.5-flash-lite":{"draws":30,"losses":19,"wins":17},"google/gemini-3.6-flash":{"draws":24,"losses":19,"wins":11},"google/gemini-3.8-flash":{"draws":0,"losses":10,"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":25,"wins":5},"gpt-5.4":{"draws":2,"losses":12,"wins":6},"gpt-5.4-mini":{"draws":33,"losses":9,"wins":24},"gpt-5.4-nano":{"draws":27,"losses":32,"wins":25},"gpt-5.5":{"draws":27,"losses":40,"wins":21},"gpt-5.6-luna":{"draws":8,"losses":10,"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":28,"losses":6,"wins":20},"meituan/longcat-2.0":{"draws":16,"losses":21,"wins":23},"meta/muse-glimmer-30b":{"draws":4,"losses":5,"wins":3},"meta/muse-spark-1.3":{"draws":4,"losses":14,"wins":2},"minimax/minimax-m3":{"draws":18,"losses":20,"wins":16},"mistralai/mistral-medium-3-5":{"draws":2,"losses":3,"wins":3},"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":18,"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":1},"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":12,"losses":29,"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":6,"wins":4},"x-ai/grok-4.5":{"draws":8,"losses":22,"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":6,"wins":16},"xiaomi/mimo-v2.5":{"draws":31,"losses":56,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":12,"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":9,"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":7,"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":2,"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":15,"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":7,"losses":3,"wins":2},"gpt-6-sol":{"draws":3,"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":2},"meta/muse-spark-1.2":{"draws":3,"losses":7,"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":9,"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":3},"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":11,"losses":2,"wins":9},"qwen/qwen3.8-2.4t-a95b":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-27b":{"draws":2,"losses":2,"wins":2},"qwen/qwen3.8-flash":{"draws":2,"losses":0,"wins":0},"qwen/qwen3.8-max":{"draws":3,"losses":5,"wins":2},"qwen/qwen3.8-max-0902":{"draws":8,"losses":5,"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":6,"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":4,"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":0,"losses":10,"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":2,"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":17,"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":13,"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":12,"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":2,"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":18,"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":24,"losses":16,"wins":8},"poolside/laguna-s-2.1":{"draws":22,"losses":26,"wins":6},"qwen/qwen3.7-plus":{"draws":3,"losses":7,"wins":2},"qwen/qwen3.8-2.4t-a95b":{"draws":19,"losses":21,"wins":0},"qwen/qwen3.8-27b":{"draws":6,"losses":16,"wins":4},"qwen/qwen3.8-flash":{"draws":14,"losses":11,"wins":5},"qwen/qwen3.8-max":{"draws":16,"losses":23,"wins":5},"qwen/qwen3.8-max-0902":{"draws":6,"losses":8,"wins":0},"stealth/ox-alpha":{"draws":44,"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":19,"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":0,"losses":6,"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":54,"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":20,"wins":2},"claude-opus-5-5":{"draws":0,"losses":8,"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":10,"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":31,"losses":60,"wins":73},"google/gemini-3.8-flash":{"draws":9,"losses":22,"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":5,"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":4},"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":11,"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":21,"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":2,"losses":26,"wins":76},"openai/gpt-oss-120b":{"draws":11,"losses":1,"wins":30},"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":17},"qwen/qwen3.8-max-0902":{"draws":2,"losses":0,"wins":0},"stealth/ox-alpha":{"draws":36,"losses":76,"wins":65},"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":21,"wins":24},"thinkingmachines/inkling":{"draws":14,"losses":7,"wins":43},"thinkingmachines/inkling-small":{"draws":11,"losses":5,"wins":27},"x-ai/grok-4.5":{"draws":11,"losses":42,"wins":31},"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":4,"wins":0}},"gpt-5.6-terra":{"bytedance-seed/seed-2.0-code":{"draws":19,"losses":9,"wins":20},"claude-fable-5":{"draws":12,"losses":27,"wins":1},"claude-fable-5-1":{"draws":6,"losses":38,"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":11,"wins":8},"cohere/north-mini-code":{"draws":2,"losses":1,"wins":7},"deepseek/deepseek-v4-flash":{"draws":18,"losses":12,"wins":20},"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":20,"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":5,"losses":5,"wins":2},"gpt-5.5":{"draws":4,"losses":3,"wins":1},"gpt-5.6-luna":{"draws":17,"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":4,"wins":15},"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":17,"losses":13,"wins":8},"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":23,"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":9,"wins":11},"qwen/qwen3.8-max-0902":{"draws":2,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":57,"losses":48,"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":8,"losses":1,"wins":7},"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":26,"wins":29},"claude-opus-4-5":{"draws":7,"losses":5,"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":12,"losses":5,"wins":49},"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":27},"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":7,"losses":0,"wins":23},"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":4,"losses":2,"wins":24},"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":3,"wins":32},"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":20},"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":5},"x-ai/grok-build-0.1":{"draws":1,"losses":0,"wins":5},"xiaomi/mimo-v2.5":{"draws":1,"losses":0,"wins":11},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":0,"wins":8},"xiaomi/mimo-v2.6-pro":{"draws":0,"losses":0,"wins":4},"z-ai/glm-5.2":{"draws":6,"losses":2,"wins":30},"z-ai/glm-5.3":{"draws":10,"losses":5,"wins":31},"z-ai/glm-5.3-flash":{"draws":10,"losses":5,"wins":37},"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":0,"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":2,"losses":0,"wins":2},"deepseek/deepseek-v4-pro-0813":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4.1-flash":{"draws":10,"losses":5,"wins":1},"google/gemini-3.1-flash-lite":{"draws":2,"losses":0,"wins":2},"google/gemini-3.5-flash":{"draws":5,"losses":9,"wins":6},"google/gemini-3.5-flash-lite":{"draws":2,"losses":2,"wins":2},"google/gemini-3.6-flash":{"draws":5,"losses":7,"wins":0},"google/gemini-3.8-flash":{"draws":0,"losses":4,"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":7,"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":2,"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":3,"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":2,"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":4,"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},"thinkingmachines/inkling":{"draws":4,"losses":0,"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":2,"losses":0,"wins":0},"xiaomi/mimo-v2.5":{"draws":9,"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":11,"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":1,"losses":2,"wins":7},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":2,"wins":5},"google/gemini-3.1-flash-lite":{"draws":3,"losses":0,"wins":5},"google/gemini-3.5-flash":{"draws":2,"losses":7,"wins":5},"google/gemini-3.5-flash-lite":{"draws":2,"losses":3,"wins":13},"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":3,"wins":7},"gpt-5.4-nano":{"draws":2,"losses":2,"wins":6},"gpt-5.5":{"draws":1,"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":4},"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},"meituan/longcat-2.0":{"draws":0,"losses":1,"wins":7},"meta/muse-glimmer-30b":{"draws":2,"losses":0,"wins":6},"meta/muse-spark-1.2":{"draws":2,"losses":2,"wins":2},"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":0,"losses":0,"wins":2},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":4},"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":4},"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":0,"wins":2},"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":9},"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":3,"wins":3},"z-ai/glm-5.3-flash":{"draws":1,"losses":3,"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":14,"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":2},"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":10,"losses":9,"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":12,"wins":1},"gpt-5.6-terra":{"draws":14,"losses":8,"wins":6},"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":7,"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":11,"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":41,"losses":45,"wins":21},"stepfun/step-3.7-flash":{"draws":2,"losses":5,"wins":3},"tencent/hy3-preview":{"draws":6,"losses":0,"wins":2},"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":6,"wins":0},"claude-opus-4-5":{"draws":27,"losses":21,"wins":6},"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":12,"wins":3},"cohere/north-mini-code":{"draws":26,"losses":6,"wins":10},"deepseek/deepseek-v4-flash":{"draws":34,"losses":24,"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":9,"losses":15,"wins":2},"google/gemini-3.1-flash-lite":{"draws":14,"losses":23,"wins":11},"google/gemini-3.5-flash":{"draws":11,"losses":7,"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":9,"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":20},"gpt-5.4":{"draws":4,"losses":8,"wins":0},"gpt-5.4-mini":{"draws":30,"losses":15,"wins":7},"gpt-5.4-nano":{"draws":39,"losses":22,"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":6,"wins":2},"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":12,"wins":4},"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":9,"wins":2},"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":9,"losses":18,"wins":1},"stealth/ox-alpha":{"draws":19,"losses":25,"wins":2},"stepfun/step-3.7-flash":{"draws":18,"losses":12,"wins":2},"tencent/hy3-preview":{"draws":13,"losses":19,"wins":4},"tencent/hy4-preview":{"draws":3,"losses":5,"wins":2},"thinkingmachines/inkling":{"draws":31,"losses":26,"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":51,"losses":36,"wins":21},"xiaomi/mimo-v2.5-pro":{"draws":19,"losses":17,"wins":12},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":3,"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":4,"losses":8,"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":10,"wins":3},"cohere/north-mini-code":{"draws":31,"losses":3,"wins":16},"deepseek/deepseek-v4-flash":{"draws":24,"losses":20,"wins":20},"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":45,"wins":13},"google/gemini-3.6-flash":{"draws":39,"losses":37,"wins":28},"google/gemini-3.8-flash":{"draws":6,"losses":16,"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":33,"wins":20},"gpt-5.4":{"draws":13,"losses":11,"wins":4},"gpt-5.4-mini":{"draws":28,"losses":21,"wins":21},"gpt-5.4-nano":{"draws":24,"losses":52,"wins":34},"gpt-5.5":{"draws":40,"losses":17,"wins":17},"gpt-5.6-luna":{"draws":6,"losses":6,"wins":6},"gpt-5.6-sol":{"draws":0,"losses":26,"wins":0},"gpt-5.6-terra":{"draws":11,"losses":9,"wins":2},"gpt-6-astra":{"draws":2,"losses":16,"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":5,"losses":22,"wins":3},"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":6,"losses":13,"wins":9},"poolside/laguna-s-2.1":{"draws":52,"losses":41,"wins":25},"qwen/qwen3.7-max":{"draws":25,"losses":18,"wins":5},"qwen/qwen3.7-plus":{"draws":13,"losses":12,"wins":11},"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":15,"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":16,"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":51,"losses":48,"wins":53},"xiaomi/mimo-v2.5-pro":{"draws":22,"losses":31,"wins":13},"xiaomi/mimo-v2.6-flash":{"draws":4,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":6,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":40,"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":7,"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":17,"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":25,"losses":29,"wins":4},"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":13,"wins":2},"meta/muse-spark-1.3":{"draws":8,"losses":12,"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":4,"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":14,"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":12,"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":2,"wins":0},"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":22,"wins":5},"claude-fable-5-1":{"draws":6,"losses":42,"wins":0},"claude-opus-4-5":{"draws":23,"losses":30,"wins":25},"claude-opus-4-8":{"draws":8,"losses":13,"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":15},"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":26,"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":10,"losses":16,"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":27,"wins":6},"meta/muse-spark-1.3":{"draws":9,"losses":19,"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":17,"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":10,"losses":6,"wins":22},"poolside/laguna-s-2.1":{"draws":16,"losses":10,"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":12,"losses":19,"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":10,"losses":27,"wins":15},"thinkingmachines/inkling":{"draws":30,"losses":13,"wins":31},"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":29,"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":3,"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":19,"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":19,"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":18,"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":3,"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":13,"losses":21,"wins":8},"gpt-5.4-mini":{"draws":6,"losses":0,"wins":4},"gpt-5.4-nano":{"draws":2,"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":25,"wins":2},"gpt-5.6-terra":{"draws":10,"losses":20,"wins":14},"gpt-6-astra":{"draws":3,"losses":19,"wins":2},"gpt-6-luna":{"draws":2,"losses":3,"wins":3},"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":17},"inclusionai/ling-3.0-flash":{"draws":5,"losses":4,"wins":13},"meituan/longcat-2.0":{"draws":14,"losses":5,"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":4,"losses":12,"wins":2},"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":4,"losses":3,"wins":3},"o3":{"draws":12,"losses":24,"wins":12},"openai/gpt-oss-120b":{"draws":22,"losses":9,"wins":21},"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":6,"losses":2,"wins":0},"stealth/ox-alpha":{"draws":46,"losses":72,"wins":26},"stepfun/step-3.7-flash":{"draws":4,"losses":6,"wins":10},"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":3},"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":2,"losses":5,"wins":3},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":3,"wins":0},"z-ai/glm-5.2":{"draws":17,"losses":18,"wins":19},"z-ai/glm-5.3":{"draws":10,"losses":25,"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":2,"wins":1},"deepseek/deepseek-v4-pro-0813":{"draws":1,"losses":1,"wins":2},"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":6,"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":2,"wins":0},"moonshotai/kimi-k3":{"draws":7,"losses":11,"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":15,"wins":6},"openai/gpt-oss-120b":{"draws":2,"losses":7,"wins":3},"poolside/laguna-s-2.1":{"draws":6,"losses":9,"wins":13},"qwen/qwen3.7-max":{"draws":15,"losses":14,"wins":5},"qwen/qwen3.7-plus":{"draws":7,"losses":6,"wins":7},"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":10,"wins":3},"x-ai/grok-4.6":{"draws":2,"losses":10,"wins":0},"x-ai/grok-4.7":{"draws":0,"losses":2,"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":14,"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":14,"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":0,"losses":1,"wins":1},"deepseek/deepseek-v4-flash":{"draws":16,"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":3,"losses":3,"wins":2},"google/gemini-3.5-flash":{"draws":9,"losses":19,"wins":4},"google/gemini-3.5-flash-lite":{"draws":25,"losses":38,"wins":17},"google/gemini-3.6-flash":{"draws":24,"losses":31,"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":5,"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":20,"losses":17,"wins":5},"meta/muse-spark-1.2":{"draws":10,"losses":19,"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":18,"wins":0},"nex-agi/nex-n2-pro":{"draws":7,"losses":2,"wins":5},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":8,"losses":2,"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":30,"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":2,"losses":4,"wins":4},"xiaomi/mimo-v2.5-pro":{"draws":1,"losses":4,"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":15,"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":31,"losses":20,"wins":49},"cohere/north-mini-code":{"draws":4,"losses":1,"wins":11},"deepseek/deepseek-v4-flash":{"draws":17,"losses":18,"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":8},"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":6},"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":16,"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":16,"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":20},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":2,"wins":2},"moonshotai/kimi-k3":{"draws":34,"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":17,"losses":54,"wins":51},"openai/gpt-oss-120b":{"draws":12,"losses":8,"wins":22},"poolside/laguna-s-2.1":{"draws":33,"losses":11,"wins":42},"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":5,"wins":2},"stealth/ox-alpha":{"draws":38,"losses":61,"wins":53},"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":30,"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":30,"losses":11,"wins":23},"z-ai/glm-5.3":{"draws":11,"losses":22,"wins":13},"z-ai/glm-5.3-flash":{"draws":11,"losses":23,"wins":8},"z-ai/glm-5.3-flashx":{"draws":3,"losses":3,"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":6,"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":7,"losses":5,"wins":2},"deepseek/deepseek-v4.1-flash":{"draws":0,"losses":3,"wins":1},"google/gemini-3.1-flash-lite":{"draws":14,"losses":5,"wins":11},"google/gemini-3.5-flash":{"draws":6,"losses":6,"wins":4},"google/gemini-3.5-flash-lite":{"draws":24,"losses":3,"wins":3},"google/gemini-3.6-flash":{"draws":17,"losses":21,"wins":10},"google/gemini-3.8-flash":{"draws":1,"losses":5,"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":27,"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":10,"losses":6,"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":13,"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":15,"losses":8,"wins":9},"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":12,"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":15,"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":15,"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":7,"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":2,"wins":0},"meta/muse-spark-1.3":{"draws":1,"losses":9,"wins":0},"minimax/minimax-m3":{"draws":5,"losses":16,"wins":11},"mistralai/mistral-medium-3-5":{"draws":3,"losses":0,"wins":1},"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":11,"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":2},"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":6,"losses":9,"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":12,"losses":6,"wins":2},"xiaomi/mimo-v2.5":{"draws":24,"losses":26,"wins":22},"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":6,"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":6,"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":5},"google/gemini-3.5-flash-lite":{"draws":33,"losses":73,"wins":24},"google/gemini-3.6-flash":{"draws":37,"losses":46,"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":14},"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":7,"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":45,"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":11,"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":2,"losses":0,"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":11,"wins":13},"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":12,"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":1,"losses":5,"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":13,"wins":6},"gpt-5.4-mini":{"draws":2,"losses":2,"wins":2},"gpt-5.4-nano":{"draws":0,"losses":3,"wins":5},"gpt-5.5":{"draws":5,"losses":5,"wins":0},"gpt-5.6-luna":{"draws":17,"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":3},"inception/mercury-2.5-preview":{"draws":14,"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":2,"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":8,"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-v2.6-flash":{"draws":4,"losses":0,"wins":0},"xiaomi/mimo-v2.6-pro":{"draws":1,"losses":2,"wins":1},"z-ai/glm-5.2":{"draws":22,"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":119,"wins":10},"claude-opus-5-5":{"draws":0,"losses":12,"wins":0},"claude-sonnet-5":{"draws":8,"losses":17,"wins":1},"cohere/north-mini-code":{"draws":27,"losses":18,"wins":3},"deepseek/deepseek-v4-flash":{"draws":23,"losses":16,"wins":23},"deepseek/deepseek-v4-pro":{"draws":6,"losses":11,"wins":11},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":14,"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":14,"wins":9},"google/gemini-3.5-flash-lite":{"draws":25,"losses":30,"wins":45},"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":9},"gpt-5.4-nano":{"draws":31,"losses":22,"wins":37},"gpt-5.5":{"draws":33,"losses":21,"wins":16},"gpt-5.6-luna":{"draws":12,"losses":8,"wins":10},"gpt-5.6-sol":{"draws":6,"losses":22,"wins":2},"gpt-5.6-terra":{"draws":13,"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":10,"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":8},"meta/muse-spark-1.3":{"draws":2,"losses":13,"wins":9},"minimax/minimax-m3":{"draws":14,"losses":15,"wins":15},"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":26},"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":6},"qwen/qwen3.8-max-0902":{"draws":1,"losses":3,"wins":4},"stealth/ox-alpha":{"draws":26,"losses":46,"wins":19},"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":2,"wins":2},"x-ai/grok-build-0.1":{"draws":7,"losses":10,"wins":5},"xiaomi/mimo-v2.5":{"draws":33,"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":10,"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":16,"losses":10,"wins":16},"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":2,"wins":0},"google/gemini-3.1-flash-lite":{"draws":3,"losses":7,"wins":22},"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":9,"losses":3,"wins":18},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":22,"losses":6,"wins":14},"o3":{"draws":7,"losses":14,"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":2},"qwen/qwen3.7-plus":{"draws":14,"losses":6,"wins":14},"qwen/qwen3.8-2.4t-a95b":{"draws":5,"losses":4,"wins":1},"qwen/qwen3.8-27b":{"draws":0,"losses":7,"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":1,"wins":0},"stealth/ox-alpha":{"draws":6,"losses":21,"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":2,"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":2,"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":7,"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":15,"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":15,"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":15,"losses":17,"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":10,"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":0,"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":0,"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":9,"losses":5,"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":3,"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":21,"wins":10},"claude-fable-5-1":{"draws":2,"losses":48,"wins":0},"claude-opus-4-5":{"draws":12,"losses":17,"wins":15},"claude-opus-4-8":{"draws":10,"losses":10,"wins":4},"claude-opus-5":{"draws":1,"losses":12,"wins":5},"claude-opus-5-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":16,"losses":9,"wins":19},"cohere/north-mini-code":{"draws":0,"losses":0,"wins":14},"deepseek/deepseek-v4-flash":{"draws":20,"losses":8,"wins":28},"deepseek/deepseek-v4-pro":{"draws":13,"losses":11,"wins":20},"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":16,"wins":15},"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":6,"losses":23,"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":13},"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":1,"wins":3},"gpt-6-sol":{"draws":0,"losses":4,"wins":2},"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":22},"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":17},"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":4,"losses":8,"wins":2},"stealth/ox-alpha":{"draws":37,"losses":60,"wins":52},"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":16,"losses":7,"wins":37},"x-ai/grok-4.5":{"draws":8,"losses":19,"wins":11},"x-ai/grok-4.6":{"draws":14,"losses":17,"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":4},"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":24},"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":5,"losses":3,"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":11,"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":20,"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":23,"wins":0},"claude-fable-5-1":{"draws":4,"losses":28,"wins":0},"claude-opus-4-5":{"draws":15,"losses":21,"wins":6},"claude-opus-4-8":{"draws":1,"losses":8,"wins":1},"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":3,"wins":5},"gpt-4.1":{"draws":0,"losses":2,"wins":4},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":2},"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":5,"wins":0},"gpt-5.6-luna":{"draws":17,"losses":19,"wins":10},"gpt-5.6-sol":{"draws":4,"losses":24,"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":15,"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-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":14,"losses":26,"wins":10},"openai/gpt-oss-120b":{"draws":18,"losses":18,"wins":14},"poolside/laguna-s-2.1":{"draws":15,"losses":12,"wins":13},"qwen/qwen3.7-max":{"draws":9,"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":6},"qwen/qwen3.8-max-0902":{"draws":3,"losses":3,"wins":2},"stealth/ox-alpha":{"draws":41,"losses":69,"wins":26},"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":25,"losses":15,"wins":16},"x-ai/grok-4.5":{"draws":9,"losses":12,"wins":5},"x-ai/grok-4.6":{"draws":17,"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":28,"losses":18,"wins":16},"z-ai/glm-5.3":{"draws":11,"losses":27,"wins":4},"z-ai/glm-5.3-flash":{"draws":16,"losses":13,"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":20,"losses":21,"wins":13},"claude-fable-5":{"draws":8,"losses":7,"wins":17},"claude-fable-5-1":{"draws":0,"losses":33,"wins":3},"claude-opus-4-5":{"draws":14,"losses":15,"wins":13},"claude-opus-4-8":{"draws":1,"losses":5,"wins":4},"claude-opus-5":{"draws":4,"losses":15,"wins":1},"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":12,"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":14,"losses":9,"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":9,"losses":11,"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":8},"gpt-5.4":{"draws":18,"losses":11,"wins":21},"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":0,"losses":26,"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":11,"wins":11},"meta/muse-spark-1.3":{"draws":6,"losses":10,"wins":8},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":2},"mistralai/mistral-medium-3-5":{"draws":11,"losses":7,"wins":12},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":0,"wins":0},"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":2,"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":2,"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":6,"wins":6},"qwen/qwen3.8-max":{"draws":19,"losses":27,"wins":10},"qwen/qwen3.8-max-0902":{"draws":2,"losses":4,"wins":2},"stealth/ox-alpha":{"draws":47,"losses":51,"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},"xiaomi/mimo-v2.5":{"draws":11,"losses":3,"wins":10},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":2,"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":6,"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":9,"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":10},"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":3},"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":10,"losses":3,"wins":1},"gpt-6-sol":{"draws":3,"losses":10,"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":6,"losses":0,"wins":2},"meta/muse-spark-1.2":{"draws":1,"losses":1,"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":3},"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":4,"losses":0,"wins":2},"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":8,"losses":11,"wins":9},"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":4,"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":6,"losses":12,"wins":4},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":5,"wins":3},"z-ai/glm-5.2":{"draws":11,"losses":1,"wins":6},"z-ai/glm-5.3":{"draws":6,"losses":2,"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":60,"losses":32,"wins":62},"claude-fable-5":{"draws":38,"losses":85,"wins":23},"claude-fable-5-1":{"draws":9,"losses":152,"wins":1},"claude-opus-4-5":{"draws":61,"losses":48,"wins":37},"claude-opus-4-8":{"draws":16,"losses":12,"wins":10},"claude-opus-5":{"draws":8,"losses":65,"wins":5},"claude-opus-5-5":{"draws":2,"losses":30,"wins":0},"claude-sonnet-5":{"draws":59,"losses":51,"wins":48},"cohere/north-mini-code":{"draws":9,"losses":3,"wins":14},"deepseek/deepseek-v4-flash":{"draws":94,"losses":48,"wins":40},"deepseek/deepseek-v4-pro":{"draws":75,"losses":59,"wins":44},"deepseek/deepseek-v4-pro-0813":{"draws":70,"losses":55,"wins":43},"deepseek/deepseek-v4.1-flash":{"draws":3,"losses":21,"wins":14},"google/gemini-3.1-flash-lite":{"draws":8,"losses":0,"wins":12},"google/gemini-3.5-flash":{"draws":56,"losses":76,"wins":42},"google/gemini-3.5-flash-lite":{"draws":121,"losses":88,"wins":109},"google/gemini-3.6-flash":{"draws":85,"losses":111,"wins":84},"google/gemini-3.8-flash":{"draws":57,"losses":78,"wins":27},"google/gemma-4-31b-it":{"draws":7,"losses":2,"wins":11},"gpt-4.1":{"draws":9,"losses":3,"wins":6},"gpt-4.1-nano":{"draws":1,"losses":1,"wins":4},"gpt-5":{"draws":18,"losses":9,"wins":13},"gpt-5.4":{"draws":74,"losses":65,"wins":17},"gpt-5.4-mini":{"draws":10,"losses":14,"wins":14},"gpt-5.4-nano":{"draws":9,"losses":7,"wins":24},"gpt-5.5":{"draws":16,"losses":7,"wins":5},"gpt-5.6-luna":{"draws":80,"losses":46,"wins":42},"gpt-5.6-sol":{"draws":29,"losses":89,"wins":26},"gpt-5.6-terra":{"draws":74,"losses":46,"wins":38},"gpt-6-astra":{"draws":13,"losses":119,"wins":0},"gpt-6-luna":{"draws":12,"losses":6,"wins":4},"gpt-6-sol":{"draws":7,"losses":15,"wins":4},"ibm-granite/granite-4.2-8b":{"draws":19,"losses":1,"wins":6},"inception/mercury-2.5-preview":{"draws":53,"losses":10,"wins":49},"inclusionai/ling-3.0-flash":{"draws":25,"losses":12,"wins":15},"meituan/longcat-2.0":{"draws":35,"losses":13,"wins":61},"meta/muse-glimmer-30b":{"draws":80,"losses":30,"wins":60},"meta/muse-spark-1.2":{"draws":41,"losses":42,"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":56,"losses":41,"wins":35},"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":35,"losses":74,"wins":51},"openai/gpt-oss-120b":{"draws":75,"losses":28,"wins":51},"poolside/laguna-s-2.1":{"draws":58,"losses":21,"wins":41},"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":34,"losses":33,"wins":29},"qwen/qwen3.8-flash":{"draws":48,"losses":30,"wins":20},"qwen/qwen3.8-max":{"draws":61,"losses":71,"wins":42},"qwen/qwen3.8-max-0902":{"draws":7,"losses":19,"wins":8},"stealth/ox-alpha":{"draws":169,"losses":286,"wins":172},"stepfun/step-3.7-flash":{"draws":12,"losses":12,"wins":18},"tencent/hy3-preview":{"draws":16,"losses":2,"wins":8},"tencent/hy4-preview":{"draws":57,"losses":74,"wins":31},"thinkingmachines/inkling":{"draws":58,"losses":19,"wins":53},"thinkingmachines/inkling-small":{"draws":92,"losses":32,"wins":68},"x-ai/grok-4.5":{"draws":45,"losses":43,"wins":32},"x-ai/grok-4.6":{"draws":70,"losses":59,"wins":33},"x-ai/grok-4.7":{"draws":1,"losses":6,"wins":3},"x-ai/grok-build-0.1":{"draws":8,"losses":5,"wins":9},"xiaomi/mimo-v2.5":{"draws":28,"losses":19,"wins":23},"xiaomi/mimo-v2.5-pro":{"draws":7,"losses":11,"wins":8},"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":98,"losses":56,"wins":72},"z-ai/glm-5.3":{"draws":31,"losses":82,"wins":21},"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":6,"losses":35,"wins":13},"claude-opus-4-8":{"draws":0,"losses":15,"wins":1},"claude-opus-5":{"draws":0,"losses":12,"wins":0},"claude-opus-5-5":{"draws":0,"losses":12,"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":0},"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":0,"losses":0,"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":60,"wins":28},"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":12,"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":2,"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":6,"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":15,"losses":31,"wins":6},"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":24,"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":10,"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":2,"losses":6,"wins":0},"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":3,"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":7,"losses":11,"wins":6},"x-ai/grok-4.6":{"draws":5,"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":28,"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":24},"claude-fable-5":{"draws":9,"losses":23,"wins":0},"claude-fable-5-1":{"draws":3,"losses":43,"wins":0},"claude-opus-4-5":{"draws":16,"losses":22,"wins":6},"claude-opus-4-8":{"draws":7,"losses":5,"wins":8},"claude-opus-5":{"draws":5,"losses":14,"wins":3},"claude-opus-5-5":{"draws":0,"losses":8,"wins":0},"claude-sonnet-5":{"draws":20,"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":16,"losses":24,"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":6},"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":30,"wins":3},"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":5,"losses":5,"wins":12},"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":13,"losses":15,"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":7},"o3":{"draws":7,"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":2,"losses":2,"wins":0},"qwen/qwen3.7-plus":{"draws":4,"losses":1,"wins":1},"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":38,"losses":67,"wins":51},"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":19,"losses":15,"wins":18},"z-ai/glm-5.3":{"draws":8,"losses":28,"wins":6},"z-ai/glm-5.3-flash":{"draws":15,"losses":15,"wins":10}},"thinkingmachines/inkling":{"bytedance-seed/seed-2.0-code":{"draws":6,"losses":9,"wins":7},"claude-fable-5":{"draws":2,"losses":11,"wins":1},"claude-fable-5-1":{"draws":1,"losses":17,"wins":0},"claude-opus-4-5":{"draws":43,"losses":38,"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":4,"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":15},"gpt-4.1":{"draws":7,"losses":8,"wins":15},"gpt-4.1-nano":{"draws":0,"losses":4,"wins":0},"gpt-5":{"draws":24,"losses":19,"wins":7},"gpt-5.4":{"draws":6,"losses":2,"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":13,"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":17,"wins":0},"gpt-6-luna":{"draws":4,"losses":0,"wins":0},"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":5,"losses":6,"wins":7},"meta/muse-spark-1.2":{"draws":7,"losses":3,"wins":6},"meta/muse-spark-1.3":{"draws":0,"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":13,"losses":8,"wins":13},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":26,"losses":17,"wins":25},"o3":{"draws":7,"losses":28,"wins":13},"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":23,"wins":9},"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":5,"wins":1},"qwen/qwen3.8-max-0902":{"draws":5,"losses":3,"wins":0},"stealth/ox-alpha":{"draws":16,"losses":35,"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":38,"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":60,"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":29,"losses":36,"wins":23},"z-ai/glm-5.3":{"draws":3,"losses":15,"wins":4},"z-ai/glm-5.3-flash":{"draws":1,"losses":4,"wins":1},"z-ai/glm-5.3-flashx":{"draws":4,"losses":8,"wins":2}},"thinkingmachines/inkling-small":{"bytedance-seed/seed-2.0-code":{"draws":19,"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":0,"losses":6,"wins":0},"claude-opus-5":{"draws":2,"losses":9,"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":4,"wins":1},"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":37,"wins":25},"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":6,"losses":4,"wins":0},"gpt-5.4":{"draws":25,"losses":6,"wins":4},"gpt-5.4-mini":{"draws":4,"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":5,"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":7,"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":0,"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":16,"losses":13,"wins":5},"qwen/qwen3.8-max":{"draws":33,"losses":35,"wins":21},"stealth/ox-alpha":{"draws":59,"losses":56,"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":5,"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":31,"wins":9},"claude-fable-5-1":{"draws":0,"losses":36,"wins":4},"claude-opus-4-5":{"draws":35,"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":15,"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":87,"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":6},"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":3,"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":6,"losses":2,"wins":10},"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":16,"wins":15},"qwen/qwen3.8-max-0902":{"draws":1,"losses":2,"wins":5},"stealth/ox-alpha":{"draws":40,"losses":54,"wins":42},"stepfun/step-3.7-flash":{"draws":4,"losses":8,"wins":16},"tencent/hy3-preview":{"draws":5,"losses":4,"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":5,"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-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":7,"losses":22,"wins":11}},"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":13},"claude-opus-4-8":{"draws":7,"losses":5,"wins":2},"claude-opus-5":{"draws":3,"losses":25,"wins":2},"claude-opus-5-5":{"draws":2,"losses":10,"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":19,"losses":9,"wins":22},"deepseek/deepseek-v4-pro":{"draws":16,"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":29},"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-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":28,"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":2,"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":13},"meta/muse-spark-1.2":{"draws":12,"losses":9,"wins":17},"meta/muse-spark-1.3":{"draws":14,"losses":22,"wins":14},"minimax/minimax-m3":{"draws":2,"losses":0,"wins":6},"mistralai/mistral-medium-3-5":{"draws":17,"losses":3,"wins":8},"moonshotai/kimi-k3":{"draws":11,"losses":17,"wins":16},"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":25},"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":21,"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":5,"losses":3,"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":2,"losses":0,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":4,"losses":6,"wins":0},"z-ai/glm-5.2":{"draws":22,"losses":16,"wins":24},"z-ai/glm-5.3":{"draws":8,"losses":26,"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":5,"wins":5},"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":2,"losses":7,"wins":3},"claude-opus-5-5":{"draws":3,"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":4},"deepseek/deepseek-v4-pro-0813":{"draws":0,"losses":0,"wins":4},"deepseek/deepseek-v4.1-flash":{"draws":2,"losses":2,"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":4,"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":2,"losses":3,"wins":3},"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":2,"wins":2},"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-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":2,"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":2,"losses":0,"wins":0},"thinkingmachines/inkling-small":{"draws":0,"losses":0,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":2,"wins":2},"x-ai/grok-4.6":{"draws":1,"losses":4,"wins":5},"x-ai/grok-4.7":{"draws":0,"losses":9,"wins":1},"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":10,"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":31,"wins":0},"claude-opus-4-5":{"draws":45,"losses":57,"wins":36},"claude-opus-4-8":{"draws":29,"losses":67,"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":0,"losses":8,"wins":0},"deepseek/deepseek-v4-pro-0813":{"draws":9,"losses":11,"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":12,"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":22,"wins":25},"gpt-5.4-nano":{"draws":25,"losses":60,"wins":53},"gpt-5.5":{"draws":35,"losses":33,"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":5,"losses":21,"wins":2},"gpt-6-astra":{"draws":1,"losses":23,"wins":0},"gpt-6-luna":{"draws":5,"losses":3,"wins":4},"gpt-6-sol":{"draws":4,"losses":14,"wins":0},"ibm-granite/granite-4.2-8b":{"draws":2,"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":14,"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":40,"wins":9},"nex-agi/nex-n2-pro":{"draws":13,"losses":18,"wins":25},"nvidia/nemotron-3-ultra-550b-a55b":{"draws":32,"losses":36,"wins":36},"o3":{"draws":10,"losses":32,"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":14,"wins":5},"qwen/qwen3.8-max-0902":{"draws":14,"losses":9,"wins":1},"stealth/ox-alpha":{"draws":15,"losses":57,"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":40},"thinkingmachines/inkling-small":{"draws":8,"losses":8,"wins":4},"x-ai/grok-4.5":{"draws":12,"losses":24,"wins":8},"x-ai/grok-4.6":{"draws":12,"losses":13,"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":0,"losses":4,"wins":0},"z-ai/glm-5.2":{"draws":37,"losses":51,"wins":28},"z-ai/glm-5.3":{"draws":6,"losses":14,"wins":0},"z-ai/glm-5.3-flash":{"draws":2,"losses":12,"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":21,"wins":13},"claude-opus-4-8":{"draws":11,"losses":9,"wins":10},"claude-opus-5":{"draws":3,"losses":52,"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":11,"wins":13},"deepseek/deepseek-v4-pro":{"draws":7,"losses":10,"wins":7},"deepseek/deepseek-v4-pro-0813":{"draws":5,"losses":6,"wins":3},"deepseek/deepseek-v4.1-flash":{"draws":1,"losses":3,"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":11,"losses":13,"wins":6},"google/gemini-3.8-flash":{"draws":7,"losses":10,"wins":1},"google/gemma-4-31b-it":{"draws":2,"losses":4,"wins":10},"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":8},"gpt-5.4":{"draws":6,"losses":12,"wins":4},"gpt-5.4-mini":{"draws":5,"losses":13,"wins":10},"gpt-5.4-nano":{"draws":17,"losses":11,"wins":20},"gpt-5.5":{"draws":12,"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":2,"wins":0},"gpt-6-astra":{"draws":0,"losses":4,"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":3,"wins":3},"inclusionai/ling-3.0-flash":{"draws":17,"losses":12,"wins":15},"meituan/longcat-2.0":{"draws":21,"losses":15,"wins":16},"meta/muse-glimmer-30b":{"draws":4,"losses":2,"wins":4},"meta/muse-spark-1.2":{"draws":3,"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":1},"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":4},"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":8,"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":3},"qwen/qwen3.8-max-0902":{"draws":3,"losses":3,"wins":2},"stealth/ox-alpha":{"draws":10,"losses":23,"wins":5},"stepfun/step-3.7-flash":{"draws":10,"losses":7,"wins":11},"tencent/hy3-preview":{"draws":9,"losses":13,"wins":6},"tencent/hy4-preview":{"draws":0,"losses":4,"wins":2},"thinkingmachines/inkling":{"draws":4,"losses":9,"wins":19},"thinkingmachines/inkling-small":{"draws":8,"losses":2,"wins":4},"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":18},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":4,"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":23,"wins":17},"z-ai/glm-5.3":{"draws":5,"losses":12,"wins":1},"z-ai/glm-5.3-flash":{"draws":9,"losses":7,"wins":2},"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":0,"losses":10,"wins":0},"claude-opus-4-5":{"draws":3,"losses":3,"wins":0},"claude-opus-4-8":{"draws":2,"losses":0,"wins":2},"claude-opus-5":{"draws":0,"losses":6,"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":9,"losses":2,"wins":5},"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":2},"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":0},"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":5,"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":2,"wins":0},"meta/muse-spark-1.3":{"draws":2,"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":5,"wins":12},"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":4,"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":4,"losses":8,"wins":8},"stealth/ox-alpha":{"draws":4,"losses":13,"wins":7},"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":4},"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":3,"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":3},"claude-fable-5":{"draws":0,"losses":10,"wins":0},"claude-fable-5-1":{"draws":1,"losses":9,"wins":0},"claude-opus-4-5":{"draws":0,"losses":2,"wins":4},"claude-opus-4-8":{"draws":0,"losses":8,"wins":2},"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":2,"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":2,"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":5,"wins":1},"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":3,"wins":2},"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":1,"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":4,"losses":7,"wins":1},"qwen/qwen3.8-max-0902":{"draws":7,"losses":13,"wins":10},"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":4},"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":3,"wins":5},"x-ai/grok-4.6":{"draws":5,"losses":5,"wins":4},"x-ai/grok-4.7":{"draws":5,"losses":23,"wins":2},"xiaomi/mimo-v2.5":{"draws":1,"losses":1,"wins":6},"xiaomi/mimo-v2.5-pro":{"draws":0,"losses":2,"wins":0},"xiaomi/mimo-v2.6-flash":{"draws":9,"losses":7,"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":0,"losses":6,"wins":2},"z-ai/glm-5.3-flash":{"draws":1,"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":15,"losses":27,"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":103,"wins":17},"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":29,"wins":50},"deepseek/deepseek-v4-pro":{"draws":22,"losses":31,"wins":23},"deepseek/deepseek-v4-pro-0813":{"draws":27,"losses":29,"wins":22},"deepseek/deepseek-v4.1-flash":{"draws":5,"losses":12,"wins":9},"google/gemini-3.1-flash-lite":{"draws":21,"losses":14,"wins":49},"google/gemini-3.5-flash":{"draws":25,"losses":31,"wins":28},"google/gemini-3.5-flash-lite":{"draws":58,"losses":71,"wins":51},"google/gemini-3.6-flash":{"draws":49,"losses":51,"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":24,"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":50,"wins":8},"gpt-5.6-terra":{"draws":30,"losses":29,"wins":15},"gpt-6-astra":{"draws":1,"losses":43,"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":41,"losses":31,"wins":54},"meta/muse-glimmer-30b":{"draws":36,"losses":13,"wins":23},"meta/muse-spark-1.2":{"draws":18,"losses":28,"wins":22},"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":28,"losses":7,"wins":23},"moonshotai/kimi-k2.7-code":{"draws":2,"losses":13,"wins":11},"moonshotai/kimi-k3":{"draws":26,"losses":24,"wins":16},"nex-agi/nex-n2-pro":{"draws":19,"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":31,"losses":18,"wins":21},"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":27,"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":14,"wins":2},"stealth/ox-alpha":{"draws":60,"losses":106,"wins":52},"stepfun/step-3.7-flash":{"draws":17,"losses":12,"wins":17},"tencent/hy3-preview":{"draws":20,"losses":13,"wins":23},"tencent/hy4-preview":{"draws":19,"losses":27,"wins":14},"thinkingmachines/inkling":{"draws":33,"losses":31,"wins":36},"thinkingmachines/inkling-small":{"draws":40,"losses":22,"wins":26},"x-ai/grok-4.5":{"draws":24,"losses":50,"wins":16},"x-ai/grok-4.6":{"draws":19,"losses":31,"wins":4},"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":62,"losses":40,"wins":60},"xiaomi/mimo-v2.5-pro":{"draws":23,"losses":24,"wins":21},"xiaomi/mimo-v2.6-flash":{"draws":1,"losses":7,"wins":2},"xiaomi/mimo-v2.6-pro":{"draws":2,"losses":2,"wins":4},"z-ai/glm-5.2":{"draws":54,"losses":49,"wins":39},"z-ai/glm-5.3":{"draws":19,"losses":39,"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":18,"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":15,"losses":12,"wins":13},"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":1,"wins":2},"gpt-4.1-nano":{"draws":0,"losses":0,"wins":4},"gpt-5":{"draws":0,"losses":3,"wins":11},"gpt-5.4":{"draws":20,"losses":31,"wins":11},"gpt-5.4-mini":{"draws":4,"losses":0,"wins":0},"gpt-5.4-nano":{"draws":4,"losses":7,"wins":7},"gpt-5.5":{"draws":4,"losses":3,"wins":5},"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":2,"losses":2,"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":14},"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":8},"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":19,"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":5,"losses":21,"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":17,"losses":18,"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":2},"tencent/hy4-preview":{"draws":13,"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":23,"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":2,"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":2,"losses":1,"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":13,"losses":22,"wins":21},"claude-opus-4-8":{"draws":5,"losses":4,"wins":1},"claude-opus-5":{"draws":5,"losses":17,"wins":6},"claude-opus-5-5":{"draws":2,"losses":8,"wins":0},"claude-sonnet-5":{"draws":15,"losses":18,"wins":17},"cohere/north-mini-code":{"draws":2,"losses":0,"wins":0},"deepseek/deepseek-v4-flash":{"draws":24,"losses":11,"wins":13},"deepseek/deepseek-v4-pro":{"draws":16,"losses":10,"wins":20},"deepseek/deepseek-v4-pro-0813":{"draws":15,"losses":20,"wins":15},"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":28,"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":2},"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":26,"wins":9},"gpt-5.6-terra":{"draws":13,"losses":10,"wins":13},"gpt-6-astra":{"draws":8,"losses":32,"wins":2},"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":3},"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":15,"losses":16,"wins":9},"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":6},"xiaomi/mimo-v2.5-pro":{"draws":2,"losses":1,"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":17,"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":0,"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":1},"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":8,"losses":4,"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":6,"wins":1},"google/gemini-3.8-flash":{"draws":0,"losses":1,"wins":1},"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":5},"gpt-5.6-sol":{"draws":3,"losses":2,"wins":1},"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":0,"losses":2,"wins":2},"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":9},"openai/gpt-oss-120b":{"draws":2,"losses":0,"wins":0},"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":1,"losses":2,"wins":7},"qwen/qwen3.8-flash":{"draws":3,"losses":4,"wins":3},"qwen/qwen3.8-max":{"draws":6,"losses":2,"wins":0},"qwen/qwen3.8-max-0902":{"draws":6,"losses":8,"wins":4},"stealth/ox-alpha":{"draws":5,"losses":15,"wins":10},"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":5,"losses":0,"wins":7},"thinkingmachines/inkling-small":{"draws":3,"losses":1,"wins":2},"x-ai/grok-4.5":{"draws":2,"losses":3,"wins":1},"x-ai/grok-4.6":{"draws":6,"losses":4,"wins":0},"x-ai/grok-4.7":{"draws":5,"losses":15,"wins":6},"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":8,"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":3,"wins":0},"z-ai/glm-5.3-flashx":{"draws":4,"losses":12,"wins":8}}}}}